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

    Neuronpedia

    INDEX
    Explanations

    instances of significant numerical values and references in the text

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

    proper nouns and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хьтан
    -0.69
    Климат
    -0.66
     defaultstate
    -0.64
    المشاركات
    -0.61
    Pautan
    -0.61
     Meksiku
    -0.60
     للاسماء
    -0.59
    setupUi
    -0.55
    GenerationType
    -0.55
     ModelRenderer
    -0.55
    POSITIVE LOGITS
    EndContext
    0.46
     anuales
    0.37
     literario
    0.36
    Skocz
    0.35
     contribuye
    0.35
     Passing
    0.34
     kullanılır
    0.34
     BytesLike
    0.33
     Notable
    0.33
     époux
    0.33
    Act Density 0.003%

    No Known Activations