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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Backdrop
    -0.08
     Leicester
    -0.07
    ONT
    -0.07
     Duel
    -0.07
     spam
    -0.07
     Gmail
    -0.07
    Publication
    -0.07
     scores
    -0.06
     δε
    -0.06
     Conway
    -0.06
    POSITIVE LOGITS
    fulWidget
    0.07
     useForm
    0.07
    );?>↵
    0.06
     pró
    0.06
     -----------
    0.06
    empor
    0.06
    lardı
    0.06
    )$
    0.06
    _'.$
    0.06
    (ROOT
    0.06
    Act Density 0.128%

    No Known Activations