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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cerrar
    -0.07
    엉
    -0.07
    (pol
    -0.07
    嚚
    -0.07
    NSError
    -0.07
     (!((
    -0.06
    ὂ
    -0.06
     Marr
    -0.06
    ✗
    -0.06
    ☓
    -0.06
    POSITIVE LOGITS
     trava
    0.07
     바랍니다
    0.07
    'eau
    0.07
    riends
    0.07
    agers
    0.07
    贪
    0.07
    报复
    0.07
     visions
    0.06
    Compilation
    0.06
     الملك
    0.06
    Act Density 0.002%

    No Known Activations