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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .PR
    -0.07
    UGE
    -0.07
     cellForRowAt
    -0.06
    項目
    -0.06
    (rc
    -0.06
    dělen
    -0.06
     adversaries
    -0.06
    ющий
    -0.06
    دار
    -0.06
     dav
    -0.06
    POSITIVE LOGITS
    _CSV
    0.07
    info
    0.07
    Identification
    0.07
    右
    0.07
     Hundred
    0.07
     Tues
    0.07
    ोम
    0.07
     silently
    0.06
    تان
    0.06
     dangerously
    0.06
    Act Density 0.001%

    No Known Activations