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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Isl
    -0.07
    .addTo
    -0.07
     Need
    -0.06
    bbbb
    -0.06
     Baylor
    -0.06
     IPP
    -0.06
    орту
    -0.06
     Austin
    -0.06
     DEFIN
    -0.06
    stdlib
    -0.06
    POSITIVE LOGITS
     on
    0.08
    ON
    0.06
     phòng
    0.06
    .source
    0.06
    ヒ
    0.06
    _None
    0.06
    컨
    0.06
    (fe
    0.06
     replacement
    0.06
    .compile
    0.06
    Act Density 0.111%

    No Known Activations