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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     canc
    -0.07
     learns
    -0.06
     booster
    -0.06
    -vers
    -0.06
     ویر
    -0.06
    .showToast
    -0.06
     XSS
    -0.06
     "('
    -0.06
    벤
    -0.06
    _CHO
    -0.06
    POSITIVE LOGITS
     зна
    0.08
     With
    0.07
     with
    0.07
     pronounced
    0.07
    фици
    0.07
     Zust
    0.06
    στημα
    0.06
    ्रद
    0.06
     paired
    0.06
    VL
    0.06
    Act Density 0.015%

    No Known Activations