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

    Neuronpedia

    INDEX
    Explanations

    end of phrase punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     This
    1.16
     These
    1.06
     Perhaps
    1.05
     Unless
    1.02
     There
    0.97
     Then
    0.95
     Öncelikle
    0.92
     While
    0.90
     Those
    0.90
     Each
    0.89
    POSITIVE LOGITS
    ,
    1.14
    ،
    0.88
     。,
    0.83
    -,
    0.80
    ,}$
    0.79
    、
    0.79
     、,
    0.72
    οντας
    0.72
    $.}
    0.70
     рэгістрацыі
    0.69
    Act Density 1.015%

    No Known Activations