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

    Neuronpedia

    INDEX
    Explanations

    coding constructs and utilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     general
    0.43
     identifying
    0.43
     healthy
    0.41
     slightly
    0.41
     Watertown
    0.40
     [
    0.38
     asking
    0.38
     establishing
    0.38
     small
    0.38
     lent
    0.37
    POSITIVE LOGITS
    मीटर
    0.47
    Finder
    0.46
    Demo
    0.45
    ariş
    0.44
    finden
    0.44
    Tester
    0.43
    डी
    0.42
    дер
    0.41
    Telefon
    0.41
    𝓮
    0.41
    Act Density 0.010%

    No Known Activations