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

    Neuronpedia

    INDEX
    Explanations

    rm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InChildren
    -0.08
    moon
    -0.07
    SeekBar
    -0.07
    计划生育
    -0.07
     erotiske
    -0.07
    ung
    -0.07
    ובש
    -0.07
    .emplace
    -0.07
     sprung
    -0.07
    中秋
    -0.07
    POSITIVE LOGITS
     CHANNEL
    0.08
    둁
    0.07
     האישי
    0.06
    𬤝
    0.06
     taps
    0.06
    移到
    0.06
    .Stage
    0.06
    惯例
    0.06
     אזר
    0.06
    -treated
    0.06
    Act Density 0.000%

    No Known Activations