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

    Neuronpedia

    INDEX
    Explanations

    problems, disturbances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.84
     незавершена
    -0.84
    AndEndTag
    -0.83
    Datuak
    -0.82
     réessayer
    -0.78
    Hauptartikel
    -0.78
    quelize
    -0.75
     שוליים
    -0.75
    writeFieldEnd
    -0.75
    onOptions
    -0.74
    POSITIVE LOGITS
     the
    0.49
     their
    0.43
     equal
    0.42
     although
    0.41
     by
    0.41
     our
    0.39
    &
    0.39
     all
    0.38
    Equal
    0.38
     made
    0.38
    Act Density 0.278%

    No Known Activations