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

    Neuronpedia

    INDEX
    Explanations

    web elements

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    G
    0.57
     gigs
    0.55
     Naked
    0.50
     bhfu
    0.50
     naked
    0.48
    涅
    0.47
     G
    0.46
    sG
    0.46
    Ink
    0.46
    njih
    0.46
    POSITIVE LOGITS
    ুতের
    0.43
    editing
    0.42
     О
    0.42
     WARRANTIES
    0.41
     Catalog
    0.41
     Per
    0.41
    utors
    0.40
    ocole
    0.40
     Editing
    0.40
    utor
    0.39
    Act Density 0.079%

    No Known Activations