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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    myModal
    -0.08
    -world
    -0.07
    earchBar
    -0.07
    עץ
    -0.07
    สงบ
    -0.07
    啮
    -0.07
     adolescence
    -0.07
     MORE
    -0.07
    ʊ
    -0.07
    _BACKGROUND
    -0.07
    POSITIVE LOGITS
    *s
    0.07
    ato
    0.07
     defer
    0.07
    ㌧
    0.07
    fh
    0.06
    倒是
    0.06
    ellt
    0.06
     VECTOR
    0.06
    Ho
    0.06
     remains
    0.06
    Act Density 0.042%

    No Known Activations