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

    Neuronpedia

    INDEX
    Explanations

    encoder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    odd
    -0.07
     superst
    -0.07
    甘肃
    -0.07
    sembl
    -0.07
    xde
    -0.06
    פרי
    -0.06
    amp
    -0.06
    TERN
    -0.06
    arseille
    -0.06
    payload
    -0.06
    POSITIVE LOGITS
    蘑菇
    0.08
    .iterator
    0.07
    EndInit
    0.07
    תכו
    0.07
    .'''↵
    0.07
    կ
    0.07
    תו
    0.06
    .Contact
    0.06
    .Linear
    0.06
    _increase
    0.06
    Act Density 0.002%

    No Known Activations