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

    Neuronpedia

    INDEX
    Explanations

    Technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    들이
    -0.07
    Beginning
    -0.07
    _playlist
    -0.07
    olving
    -0.07
     قصة
    -0.07
    NECT
    -0.07
    coming
    -0.07
    咏
    -0.07
    这段
    -0.06
     abandoning
    -0.06
    POSITIVE LOGITS
    ///
    0.07
    ро
    0.07
    gnu
    0.07
    keeper
    0.06
     ↵    ↵
    0.06
    Mir
    0.06
    #
    0.06
    cery
    0.06
     كافة
    0.06
    Park
    0.06
    Act Density 0.196%

    No Known Activations