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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    宋体
    -0.07
    _flutter
    -0.07
     velmi
    -0.07
     emotion
    -0.07
    makt
    -0.07
    "--
    -0.06
     sl
    -0.06
    MARK
    -0.06
    untas
    -0.06
     Gul
    -0.06
    POSITIVE LOGITS
     photographed
    0.07
    )?;↵
    0.07
    ↵
    0.07
    _↵
    0.06
    ()]↵↵
    0.06
    >_
    0.06
    ...↵↵↵↵↵↵
    0.06
     '__
    0.06
     například
    0.06
    redential
    0.06
    Act Density 0.000%

    No Known Activations