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

    Neuronpedia

    INDEX
    Explanations

    rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    marshaller
    -0.07
     [$
    -0.07
    ↤
    -0.07
    坽
    -0.07
    .getChannel
    -0.06
    عسكر
    -0.06
     suchen
    -0.06
    عقب
    -0.06
     hex
    -0.06
    ݬ
    -0.06
    POSITIVE LOGITS
     Astronomy
    0.08
    ខ
    0.07
     medicines
    0.07
    自助
    0.07
    ら
    0.07
     Bowling
    0.07
    escaping
    0.07
    广播
    0.07
    Aw
    0.07
     aw
    0.07
    Act Density 0.012%

    No Known Activations