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

    Neuronpedia

    INDEX
    Explanations

    correct writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ervised
    -0.06
     achie
    -0.06
    training
    -0.06
    (batch
    -0.06
    .prof
    -0.06
    sparse
    -0.05
    าตรฐาน
    -0.05
    とする
    -0.05
    (dp
    -0.05
    _registered
    -0.05
    POSITIVE LOGITS
    Report
    0.07
    лой
    0.07
    omatic
    0.07
    STATIC
    0.07
     Cl
    0.06
    merce
    0.06
    reece
    0.06
     영어
    0.06
    __[
    0.06
    cas
    0.06
    Act Density 0.013%

    No Known Activations