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

    Neuronpedia

    INDEX
    Explanations

    humans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    范围
    -0.07
    enstein
    -0.07
     İyi
    -0.06
     zdroj
    -0.06
     Bec
    -0.06
    _terms
    -0.06
     преж
    -0.06
    ynamics
    -0.06
    407
    -0.06
     Twice
    -0.06
    POSITIVE LOGITS
    :</
    0.06
     Ma
    0.06
    拒
    0.06
    瓦
    0.06
    inium
    0.06
     functor
    0.06
    utting
    0.06
    ْن
    0.06
    λα
    0.06
     Gong
    0.06
    Act Density 0.008%

    No Known Activations