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

    Neuronpedia

    INDEX
    Explanations

    duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    transform
    -0.07
    sert
    -0.07
    tested
    -0.06
     ApiService
    -0.06
    會
    -0.06
     ponds
    -0.06
    frei
    -0.06
     рек
    -0.06
    　r
    -0.06
     Metropolitan
    -0.06
    POSITIVE LOGITS
     sendData
    0.07
    _MED
    0.07
     matter
    0.06
    _triggered
    0.06
    ラク
    0.06
     smirk
    0.06
    .…
    0.06
     Stars
    0.06
    __));↵
    0.06
    υκ
    0.06
    Act Density 0.007%

    No Known Activations