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

    Neuronpedia

    INDEX
    Explanations

    programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Macro
    0.40
    akin
    0.37
     borrowed
    0.36
    Cats
    0.36
     plac
    0.36
    macro
    0.36
    सिन
    0.36
    box
    0.35
     macro
    0.35
     borrowing
    0.35
    POSITIVE LOGITS
     condensing
    0.40
    恒
    0.40
     habitudes
    0.39
    恆
    0.39
     Bén
    0.38
    裨
    0.38
     COND
    0.38
     умолча
    0.38
     uș
    0.38
    Wrapping
    0.38
    Act Density 0.026%

    No Known Activations