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

    Neuronpedia

    INDEX
    Explanations

    inquiries and reflections on personal choices and self-improvement

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

    reflection on past experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.78
    Diweddarwch
    -0.67
     snippetHide
    -0.63
    AnimationsModule
    -0.61
    fjspx
    -0.57
    SharedCtor
    -0.56
    tagHelperRunner
    -0.56
     @"/
    -0.56
    Controllo
    -0.55
    kháu
    -0.54
    POSITIVE LOGITS
    PROVIDER
    0.41
     Ful
    0.39
     warranty
    0.39
    Voltar
    0.37
    comunic
    0.37
     olvidado
    0.37
     auroit
    0.36
     recall
    0.36
     article
    0.35
    caixa
    0.34
    Act Density 0.042%

    No Known Activations