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

    Neuronpedia

    INDEX
    Explanations

    book excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    速度
    -0.08
     smoothly
    -0.07
     بگ
    -0.07
     Ver
    -0.07
    basis
    -0.07
    대로
    -0.07
    φέρει
    -0.07
    ｲ
    -0.07
    一定
    -0.07
    esc
    -0.07
    POSITIVE LOGITS
     Sync
    0.06
    .lon
    0.06
     �
    0.06
     самостоятель
    0.06
    vature
    0.05
    stackoverflow
    0.05
     pep
    0.05
     serm
    0.05
    bulan
    0.05
     congratulate
    0.05
    Act Density 0.016%

    No Known Activations