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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate absence or lack of something

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

    Follows the word "without"

    np_acts-logits-general · gemini-2.0-flash

    without certain qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.61
     sendiri
    -0.50
    ılır
    -0.47
    Or
    -0.45
     decidieron
    -0.44
     águas
    -0.43
     coleção
    -0.43
     rendah
    -0.43
     carrière
    -0.41
     automatiques
    -0.41
    POSITIVE LOGITS
     any
    1.11
     regard
    1.02
    regard
    0.89
     fail
    0.88
     necessarily
    0.85
     exception
    0.85
     interruption
    0.85
     resorting
    0.85
    (!__
    0.85
     knowing
    0.82
    Act Density 0.131%

    No Known Activations