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

    Neuronpedia

    INDEX
    Explanations

    prov

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .gstatic
    -0.08
     Nordic
    -0.08
    -CS
    -0.08
    崦
    -0.07
    빅
    -0.07
     Chaos
    -0.07
    ấy
    -0.07
    TIM
    -0.07
    CONTENT
    -0.07
    훔
    -0.07
    POSITIVE LOGITS
    ক
    0.07
     saving
    0.07
    _color
    0.07
    >v
    0.07
     profiler
    0.07
    货
    0.07
     Saving
    0.07
     bla
    0.06
     الف
    0.06
     المح
    0.06
    Act Density 0.008%

    No Known Activations