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

    Neuronpedia

    INDEX
    Explanations

    appearance and confidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '=>'
    -0.07
    Fed
    -0.06
    _TEXTURE
    -0.06
     چه
    -0.06
    htable
    -0.06
    (bounds
    -0.06
    .rmi
    -0.06
    Shop
    -0.06
    736
    -0.06
    Timer
    -0.06
    POSITIVE LOGITS
     проведення
    0.08
    agged
    0.06
    την
    0.06
    rav
    0.06
     θέση
    0.06
    crire
    0.06
    Plate
    0.06
    roe
    0.06
    _FACE
    0.06
    ilon
    0.06
    Act Density 0.075%

    No Known Activations