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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    헠
    -0.07
    ellery
    -0.07
    团员
    -0.07
    praak
    -0.06
    braco
    -0.06
    _HOT
    -0.06
    (C
    -0.06
    梢
    -0.06
    illisecond
    -0.06
    髮
    -0.06
    POSITIVE LOGITS
    -cont
    0.08
    操作
    0.07
    توج
    0.07
    SG
    0.07
    愚
    0.07
    实战
    0.07
    <IActionResult
    0.06
    	Input
    0.06
    ...↵↵↵↵↵↵
    0.06
     *>(
    0.06
    Act Density 0.005%

    No Known Activations