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

    Neuronpedia

    INDEX
    Explanations

    var

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hỏi
    -0.07
    声を
    -0.06
    ey
    -0.06
    _SERVICE
    -0.06
    ิค
    -0.06
     bile
    -0.06
    Ошибка
    -0.06
     eventual
    -0.06
    _MON
    -0.06
    板
    -0.06
    POSITIVE LOGITS
     var
    0.07
     tern
    0.06
    _bindings
    0.06
    _IMETHOD
    0.06
     panties
    0.06
    krit
    0.06
    var
    0.06
     hiring
    0.06
     scri
    0.06
     comps
    0.06
    Act Density 0.001%

    No Known Activations