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

    Neuronpedia

    INDEX
    Explanations

    scales and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iz
    -0.07
     champion
    -0.07
     Tournament
    -0.07
    .SuspendLayout
    -0.07
    浇
    -0.07
    ╇
    -0.07
     Manifest
    -0.07
     Hockey
    -0.07
     Bench
    -0.06
     pavement
    -0.06
    POSITIVE LOGITS
     SHA
    0.07
    .sec
    0.07
    CTR
    0.07
    _sin
    0.06
    .Time
    0.06
    قتر
    0.06
     dusk
    0.06
    .Character
    0.06
     işletme
    0.06
    ظر
    0.06
    Act Density 0.032%

    No Known Activations