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

    Neuronpedia

    INDEX
    Explanations

    questions related to types or categories of items and their characteristics

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

    what type or kind of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.50
    ithi
    -0.48
    ArgsConstructor
    -0.47
    UIControlState
    -0.47
    titleMargin
    -0.46
    tidine
    -0.46
     iniquity
    -0.45
     BorderSide
    -0.45
    efi
    -0.45
    PropertyChanging
    -0.44
    POSITIVE LOGITS
    cuál
    0.43
     casó
    0.40
     peor
    0.40
    そちら
    0.40
     vectorielles
    0.40
     embarazadas
    0.40
    izante
    0.40
     équilibr
    0.39
     cuál
    0.38
    culadora
    0.38
    Act Density 0.009%

    No Known Activations