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

    Neuronpedia

    INDEX
    Explanations

    understand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    visited
    -0.07
     cola
    -0.06
    tracer
    -0.06
     vợ
    -0.06
    丽
    -0.06
     refuge
    -0.06
     Cena
    -0.06
    scri
    -0.06
     edil
    -0.06
    麗
    -0.06
    POSITIVE LOGITS
    "])
    0.07
    0.07
     投稿日
    0.07
    IENCE
    0.06
     организм
    0.06
     eylem
    0.06
    گوی
    0.06
     washington
    0.06
     cihaz
    0.06
     altında
    0.06
    Act Density 0.018%

    No Known Activations