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

    Neuronpedia

    INDEX
    Explanations

    yst

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FL
    -0.07
    ativa
    -0.07
     kardeş
    -0.06
     ap
    -0.06
    يير
    -0.06
    -ar
    -0.06
     Fa
    -0.06
    érer
    -0.06
     informant
    -0.06
     clientId
    -0.06
    POSITIVE LOGITS
    escription
    0.08
    ResponseType
    0.07
    "))↵
    0.07
     operating
    0.06
     В
    0.06
     extraordinarily
    0.06
    )))↵
    0.06
     promo
    0.06
     efficiency
    0.06
    }`);↵
    0.06
    Act Density 0.001%

    No Known Activations