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

    Neuronpedia

    INDEX
    Explanations

    Sa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    以
    -0.07
     Knight
    -0.07
     thieves
    -0.07
    泣
    -0.06
    Für
    -0.06
    从
    -0.06
    更
    -0.06
     fighter
    -0.06
     Tactics
    -0.06
     knight
    -0.05
    POSITIVE LOGITS
    _sa
    0.08
     SA
    0.08
     انتقال
    0.07
    alsa
    0.07
    _EC
    0.07
    -SA
    0.07
    rott
    0.07
    asons
    0.07
    .SE
    0.07
    —is
    0.07
    Act Density 0.006%

    No Known Activations