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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts or discussions about processes and their implications

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

    process of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ModelForm
    -0.41
     myſelf
    -0.39
     pleaſure
    -0.38
     Annales
    -0.38
    ométrique
    -0.37
    ngdoc
    -0.37
     Rowe
    -0.37
    ſelf
    -0.37
    欒
    -0.36
     Eccle
    -0.36
    POSITIVE LOGITS
    hoeddwyd
    0.59
     ffilmiau
    0.48
    antMatchers
    0.43
    ----</
    0.43
     linkovi
    0.43
    يميديا
    0.41
    Aiheesta
    0.41
    Архівовано
    0.41
    Personendaten
    0.40
    EndGlobal
    0.40
    Act Density 0.341%

    No Known Activations