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

    Neuronpedia

    INDEX
    Explanations

    Lost and found

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    (Window
    -0.09
    走去
    -0.08
     Window
    -0.07
     Lessons
    -0.07
     Weston
    -0.07
    时期的
    -0.07
     hiding
    -0.07
     Pivot
    -0.07
    鑫
    -0.07
     Deliver
    -0.07
    POSITIVE LOGITS
    _SZ
    0.08
    ♬
    0.07
    普遍存在
    0.07
     acomp
    0.07
    就没有
    0.07
     하지만
    0.07
     ambiance
    0.06
     אינו
    0.06
     incontri
    0.06
     czy
    0.06
    Act Density 0.020%

    No Known Activations