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

    Neuronpedia

    INDEX
    Explanations

    "Tell me" or asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "***
    1.05
     "/",
    0.99
     "\
    0.96
     "-
    0.95
     "/
    0.95
     "{
    0.94
     praising
    0.93
     ",",
    0.91
     "..
    0.91
     "[
    0.90
    POSITIVE LOGITS
    Materials
    0.91
    scrape
    0.86
    ic
    0.85
    </
    0.80
    UTF
    0.80
    Alan
    0.79
    H
    0.79
    #
    0.79
    Sc
    0.77
    Enlaces
    0.77
    Act Density 0.001%

    No Known Activations