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

    Neuronpedia

    INDEX
    Explanations

    select store

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     réguli
    -0.65
     écrits
    -0.63
     jouets
    -0.61
     oreilles
    -0.61
     émissions
    -0.61
     communs
    -0.60
     preuves
    -0.59
     vermelhas
    -0.58
     attentes
    -0.57
     générations
    -0.56
    POSITIVE LOGITS
     the
    1.20
     their
    0.94
     his
    0.85
     a
    0.81
     our
    0.81
     some
    0.77
     an
    0.77
     its
    0.76
    <bos>
    0.74
     those
    0.70
    Act Density 0.033%

    No Known Activations