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

    Neuronpedia

    INDEX
    Explanations

    code or error messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ámara
    -0.06
    _Run
    -0.06
     بح
    -0.06
    ildiği
    -0.06
     dese
    -0.06
     minded
    -0.06
     wors
    -0.06
     Loot
    -0.06
    beam
    -0.06
     plaisir
    -0.06
    POSITIVE LOGITS
     Edison
    0.08
     paramName
    0.07
    .GetComponent
    0.07
    -non
    0.07
     localization
    0.07
    :data
    0.06
     flutter
    0.06
    JSONException
    0.06
    이가
    0.06
     dismantle
    0.06
    Act Density 0.003%

    No Known Activations