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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    French
    -0.07
    ayıp
    -0.06
    ])/
    -0.06
    CastException
    -0.06
    ulner
    -0.06
     Count
    -0.06
     scen
    -0.06
    lardır
    -0.06
    itors
    -0.06
    .function
    -0.06
    POSITIVE LOGITS
    XY
    0.07
    xy
    0.06
     универ
    0.06
     barber
    0.06
     mastur
    0.06
     lý
    0.06
    แท
    0.06
     rib
    0.06
    จะ
    0.06
     geom
    0.06
    Act Density 0.003%

    No Known Activations