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

    Neuronpedia

    INDEX
    Explanations

    Titles and Lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     capacitors
    0.25
     aziende
    0.25
     সুবিধ
    0.25
     gegeven
    0.25
     siis
    0.24
     ores
    0.24
     vantagens
    0.24
     সুবিধা
    0.24
     विश्वसनीय
    0.24
     fornecer
    0.24
    POSITIVE LOGITS
    The
    0.39
     The
    0.36
     berjudul
    0.33
     anthology
    0.30
     Untitled
    0.30
    《
    0.29
     untitled
    0.29
    the
    0.29
     Anatomy
    0.27
     THE
    0.27
    Act Density 0.112%

    No Known Activations