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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and symbols related to variables and functions

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

    math roman font commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poffe
    -0.63
    Personendaten
    -0.59
    Portail
    -0.56
    Bakgrunnsstoff
    -0.56
     ویکی‌پدی
    -0.54
    المناصب
    -0.52
     Inſ
    -0.52
     esternos
    -0.52
     Anſ
    -0.50
     ſtate
    -0.50
    POSITIVE LOGITS
    LookAnd
    0.40
    떻
    0.40
     AttributeSet
    0.37
     kasarigan
    0.37
    árbol
    0.37
    ánto
    0.37
    ніципалі
    0.37
    giaan
    0.37
    Melhor
    0.37
     recevez
    0.36
    Act Density 0.002%

    No Known Activations