Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to complex systems or procedures within technology or politics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    limitations or restrictions

    np_acts-logits-general · gemini-2.0-flash

    exclusionary and unjustifiable extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    harapkan
    -0.57
    Джерела
    -0.56
    ArgsConstructor
    -0.55
     SEDS
    -0.53
     Améli
    -0.50
     AssemblyCulture
    -0.50
    ItemBackground
    -0.50
    cèse
    -0.48
     Wicidata
    -0.48
     لينك
    -0.48
    POSITIVE LOGITS
     restrictive
    1.20
     restrictions
    1.14
     barriers
    1.13
     restriction
    1.13
     restricting
    1.10
     obstacles
    1.04
     barrier
    1.03
     restrict
    1.03
     forbidding
    1.02
     restric
    1.01
    Act Density 0.851%

    No Known Activations