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

    Neuronpedia

    INDEX
    Explanations

    storytelling formula

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Speaking
    1.45
    alah
    1.41
    skih
    1.40
    ZERO
    1.39
    Responses
    1.34
    ulkan
    1.33
     Sprague
    1.33
     mesenchymal
    1.33
    responses
    1.32
     NAD
    1.28
    POSITIVE LOGITS
    looked
    0.97
     ocul
    0.92
     lector
    0.91
     sherry
    0.91
     families
    0.91
    families
    0.91
     biliary
    0.89
     exif
    0.89
    지요
    0.88
     TOC
    0.88
    Act Density 0.001%

    No Known Activations