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

    Neuronpedia

    INDEX
    Explanations

    replace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bou
    -0.06
     خی
    -0.06
    .Hex
    -0.06
     polys
    -0.06
     CPUs
    -0.06
    "errors
    -0.06
    ㆍ동
    -0.06
    _UNS
    -0.06
    정보
    -0.06
    (simp
    -0.06
    POSITIVE LOGITS
     Birthday
    0.08
    ención
    0.07
     bás
    0.07
     tournaments
    0.07
    ologia
    0.07
     placement
    0.07
     Handles
    0.06
    общ
    0.06
    itles
    0.06
     Detector
    0.06
    Act Density 0.004%

    No Known Activations