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

    Neuronpedia

    INDEX
    Explanations

    scars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    糊涂
    -0.08
    .ps
    -0.08
    ifth
    -0.07
    lin
    -0.07
     motion
    -0.07
    绘
    -0.07
     cursor
    -0.07
    ===============
    -0.07
    Pale
    -0.07
     Skip
    -0.07
    POSITIVE LOGITS
    橦
    0.08
    天猫
    0.07
    ㏌
    0.07
     deadlock
    0.07
    䗛
    0.07
    ﯽ
    0.07
    깄
    0.06
    זכה
    0.06
    숄
    0.06
     הישראל
    0.06
    Act Density 0.003%

    No Known Activations