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

    Neuronpedia

    INDEX
    Explanations

    'lit.'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.93
    。）
    0.84
    ми
    0.81
    ?]
    0.79
    .]
    0.78
     $*$
    0.78
     “
    0.77
    ）（
    0.76
     ‘
    0.76
    -‘
    0.76
    POSITIVE LOGITS
     llegar
    1.15
     todos
    1.06
     los
    1.01
     voldo
    0.97
     tudo
    0.96
     niveau
    0.96
     manière
    0.95
     maneira
    0.95
    resolver
    0.94
     erhöht
    0.94
    Act Density 0.000%

    No Known Activations