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

    Neuronpedia

    INDEX
    Explanations

    fox

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stmt
    -0.06
    Enumeration
    -0.06
     освіти
    -0.06
     فرض
    -0.06
     Benefit
    -0.05
    �
    -0.05
    умов
    -0.05
     Ге
    -0.05
     системы
    -0.05
     authority
    -0.05
    POSITIVE LOGITS
    ')+
    0.07
    .phi
    0.07
     (~
    0.07
     touches
    0.07
    _SELF
    0.07
    ")))
    0.07
    ctions
    0.06
    ")->
    0.06
     vielleicht
    0.06
     turnout
    0.06
    Act Density 0.002%

    No Known Activations