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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lightning
    -0.07
    Pod
    -0.07
    (file
    -0.07
     Measurements
    -0.07
    یشن
    -0.06
     scales
    -0.06
    .t
    -0.06
    aps
    -0.06
     метал
    -0.06
    /man
    -0.06
    POSITIVE LOGITS
     ::=
    0.09
    :both
    0.07
    ientras
    0.07
    اجع
    0.06
    .extend
    0.06
    ัคร
    0.06
    थ
    0.06
     Ülke
    0.06
    atro
    0.06
    γωγή
    0.06
    Act Density 0.011%

    No Known Activations