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

    Neuronpedia

    INDEX
    Explanations

    improve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Romero
    -0.07
    .ids
    -0.07
     dahil
    -0.07
    -0.07
     chẳng
    -0.07
     donne
    -0.06
     nói
    -0.06
     grote
    -0.06
     ########################################################################
    -0.06
    ≥
    -0.06
    POSITIVE LOGITS
     reform
    0.07
    気持ち
    0.06
     etme
    0.06
    (relative
    0.06
     level
    0.06
    ικής
    0.06
    ilendir
    0.06
    BarButtonItem
    0.06
     změ
    0.06
     throm
    0.06
    Act Density 0.034%

    No Known Activations