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

    Neuronpedia

    INDEX
    Explanations

    knows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SECTION
    -0.07
    _signup
    -0.06
     wearing
    -0.06
    attrs
    -0.06
    썹
    -0.06
    难点
    -0.06
    _MAIN
    -0.06
    .Event
    -0.06
    完整的
    -0.06
     העיק
    -0.06
    POSITIVE LOGITS
    _:*
    0.07
     infield
    0.07
     عليها
    0.07
     pundits
    0.06
    ках
    0.06
    stdafx
    0.06
    ясь
    0.06
    接种
    0.06
    点半
    0.06
     değerlendir
    0.06
    Act Density 1.741%

    No Known Activations