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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ):
    -0.07
     reap
    -0.07
    »:
    -0.07
    Counts
    -0.06
    _),
    -0.06
    )]
    -0.06
    oop
    -0.06
    .While
    -0.06
    942
    -0.06
    ()):
    -0.06
    POSITIVE LOGITS
    caps
    0.07
     ότι
    0.07
     travail
    0.06
     가
    0.06
     Makeup
    0.06
     Gobierno
    0.06
     obsah
    0.06
     arbe
    0.06
     Annunci
    0.06
    ิก
    0.06
    Act Density 0.021%

    No Known Activations