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

    Neuronpedia

    INDEX
    Explanations

    Occupations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     freshness
    -0.07
    Woman
    -0.07
     Цент
    -0.07
     salts
    -0.06
    AES
    -0.06
    간
    -0.06
     clic
    -0.06
    �
    -0.06
    。（
    -0.06
     whitelist
    -0.06
    POSITIVE LOGITS
    	contentPane
    0.07
    Constant
    0.07
    دم
    0.06
    605
    0.06
    <double
    0.06
    .kind
    0.06
    dır
    0.06
    uida
    0.06
     tomto
    0.06
     может
    0.06
    Act Density 0.005%

    No Known Activations