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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elimination
    -0.07
    れた
    -0.07
     Friday
    -0.07
     mechanically
    -0.07
     Rao
    -0.06
     evolve
    -0.06
     melting
    -0.06
    payments
    -0.06
    ypy
    -0.06
    _paint
    -0.06
    POSITIVE LOGITS
    ΕΤ
    0.07
    fuscated
    0.07
    ger
    0.07
    .addActionListener
    0.07
    -big
    0.06
     اصفهان
    0.06
     isEnabled
    0.06
    _ABI
    0.06
     기업
    0.06
    Characters
    0.06
    Act Density 0.001%

    No Known Activations