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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     directed
    -0.07
    icus
    -0.07
     Kosten
    -0.07
    -win
    -0.06
    ча
    -0.06
     Он
    -0.06
     URLs
    -0.06
    Cancel
    -0.06
     três
    -0.06
    .getTag
    -0.06
    POSITIVE LOGITS
    낸
    0.06
    GetPosition
    0.06
     Albert
    0.06
    intval
    0.06
     відпов
    0.06
    357
    0.06
    offee
    0.06
    665
    0.06
    すぎ
    0.06
     spontaneously
    0.06
    Act Density 0.002%

    No Known Activations