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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     e
    -1.20
     y
    -0.68
     und
    -0.66
     the
    -0.63
     et
    -0.63
     a
    -0.60
     and
    -0.56
     el
    -0.52
     ed
    -0.52
    <bos>
    -0.49
    POSITIVE LOGITS
     Majefty
    1.05
     poffible
    0.90
    aarrggbb
    0.88
     Houſe
    0.88
     cauſe
    0.85
    buttonBar
    0.85
     ſche
    0.84
     BoxDecoration
    0.81
     HasFactory
    0.81
     avoient
    0.81
    Act Density 0.132%

    No Known Activations