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

    Neuronpedia

    INDEX
    Explanations

    _on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ธนา
    -0.07
    annel
    -0.07
    뜩
    -0.07
    sing
    -0.06
     Marl
    -0.06
     Sinn
    -0.06
    𨟠
    -0.06
    แสดง
    -0.06
    턱
    -0.06
    엥
    -0.06
    POSITIVE LOGITS
     Abort
    0.07
     đợi
    0.07
    几乎所有
    0.07
     rowspan
    0.07
    /results
    0.07
    _algorithm
    0.07
    Weekly
    0.07
    ,…
    0.07
     army
    0.07
    -background
    0.06
    Act Density 0.001%

    No Known Activations