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

    Neuronpedia

    INDEX
    Explanations

    Development and production

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ni
    -0.06
    ША
    -0.06
    NI
    -0.06
    аном
    -0.06
    undo
    -0.06
    =post
    -0.06
    dojo
    -0.06
    Curso
    -0.06
     shadow
    -0.06
     회
    -0.06
    POSITIVE LOGITS
    ETERS
    0.07
     democr
    0.07
    <S
    0.06
    )(↵
    0.06
    _parameter
    0.06
    <V
    0.06
    Accessory
    0.06
     aj
    0.06
    .APP
    0.06
    ')[
    0.06
    Act Density 0.041%

    No Known Activations