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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses or expressions of agreement

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

    Affirmations or agreements

    np_acts-logits-general · gemini-2.0-flash

    affirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]-'
    -0.66
    \
    -0.63
    =*/
    -0.57
    urent
    -0.57
    |<\
    -0.56
    __*/
    -0.55
    }*/
    -0.54
     termina
    -0.54
    ARING
    -0.54
    kula
    -0.53
    POSITIVE LOGITS
     Yes
    1.09
     YES
    1.07
    yes
    1.05
    YES
    1.01
    Yes
    1.01
     yes
    1.00
     indeed
    0.88
     Noyes
    0.87
     препратки
    0.80
     sì
    0.75
    Act Density 0.044%

    No Known Activations