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

    Neuronpedia

    INDEX
    Explanations

    right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (moment
    -0.07
     Berger
    -0.07
    apiro
    -0.07
    serie
    -0.07
     April
    -0.07
     August
    -0.07
    erialize
    -0.07
     motivo
    -0.06
     confidential
    -0.06
     Brisbane
    -0.06
    POSITIVE LOGITS
    ewhere
    0.06
    .vertex
    0.06
     گفت
    0.06
    ‐-
    0.06
     [\
    0.06
     constituents
    0.06
    Glyph
    0.06
    μαν
    0.06
    PAGE
    0.06
    -ne
    0.06
    Act Density 0.001%

    No Known Activations