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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mers
    -0.06
     넣
    -0.06
    _bulk
    -0.06
    Exclude
    -0.06
    Uploaded
    -0.06
     Cla
    -0.06
    cedes
    -0.06
    mousedown
    -0.06
    Int
    -0.05
    igma
    -0.05
    POSITIVE LOGITS
    芯
    0.08
     dần
    0.08
    ::$_
    0.07
    统计
    0.06
     أبي
    0.06
     нен
    0.06
     İng
    0.06
    _play
    0.06
     notamment
    0.06
    WriteBarrier
    0.06
    Act Density 0.005%

    No Known Activations