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

    Neuronpedia

    INDEX
    Explanations

    re

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sĩ
    -0.07
    Feat
    -0.07
     Gates
    -0.06
     вов
    -0.06
     Unique
    -0.06
     captured
    -0.06
    .vector
    -0.06
    Cos
    -0.06
     mientras
    -0.06
    _Output
    -0.06
    POSITIVE LOGITS
    �
    0.06
    ुआ
    0.06
    мо
    0.06
     jealous
    0.06
    uate
    0.06
     Aero
    0.06
    '});↵
    0.06
    Ї
    0.06
    >(),↵
    0.06
    ौत
    0.06
    Act Density 0.021%

    No Known Activations