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

    Neuronpedia

    INDEX
    Explanations

    illing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    streams
    -0.28
    .isDefined
    -0.25
    ä¸ĭè¡Į
    -0.25
    ä¸ĭæĿ¥çļĦ
    -0.24
     '''č↵
    -0.24
    ******č↵
    -0.24
    奢
    -0.24
    bench
    -0.24
    down
    -0.24
     **/č↵
    -0.24
    POSITIVE LOGITS
    alo
    0.27
    _guid
    0.26
    vos
    0.25
    çŃī级
    0.24
    xic
    0.24
    @author
    0.24
    ONY
    0.24
     dik
    0.24
     Luigi
    0.24
    kat
    0.24
    Act Density 0.043%

    No Known Activations