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

    Neuronpedia

    INDEX
    Explanations

    words related to political representation and implications of actions

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

    starting with "rep" or "imp"

    np_acts-logits-general · gemini-2.0-flash

    repudiate, implicate, repulsion, reprehensible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CHER
    -0.49
    ETER
    -0.47
     بلو
    -0.45
    cydow
    -0.44
     fiss
    -0.43
    Chooser
    -0.42
     dual
    -0.42
     demografica
    -0.41
     Pole
    -0.41
     dae
    -0.41
    POSITIVE LOGITS
    SequentialGroup
    0.65
     мәкал
    0.61
     GenerationType
    0.60
    :✨
    0.59
    recated
    0.58
    SharedCtor
    0.55
     addSubview
    0.54
    AxisAlignment
    0.54
    ContentAsync
    0.54
    uitable
    0.53
    Act Density 0.203%

    No Known Activations