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

    Neuronpedia

    INDEX
    Explanations

    configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    دد
    -0.08
     cyclists
    -0.08
    Datetime
    -0.07
    صح
    -0.07
     הוד
    -0.07
    同意
    -0.07
    Lim
    -0.07
    ители
    -0.07
    Ho
    -0.07
     Clash
    -0.07
    POSITIVE LOGITS
    ")]
    0.07
     Jake
    0.06
     האירוע
    0.06
    ologically
    0.06
    '><
    0.06
    낄
    0.06
     ­
    0.06
    )value
    0.06
    挽
    0.06
     Now
    0.06
    Act Density 0.090%

    No Known Activations