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

    Neuronpedia

    INDEX
    Explanations

    expressions of certainty or affirmation

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

    uncertainty or doubt

    np_acts-logits-general · gemini-2.0-flash

    absence of doubt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doesn
    -0.57
     tidak
    -0.56
     keine
    -0.56
     nggak
    -0.55
     nobody
    -0.52
     cannot
    -0.52
     doesnt
    -0.52
     isn
    -0.51
     never
    -0.50
     aren
    -0.50
    POSITIVE LOGITS
    ChildScrollView
    0.72
    enumii
    0.52
    таратура
    0.51
     Administrativna
    0.50
     protoimpl
    0.49
    adpleegd
    0.49
    wnież
    0.49
     linkovi
    0.49
     légale
    0.48
    zbęd
    0.48
    Act Density 0.252%

    No Known Activations