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

    Neuronpedia

    INDEX
    Explanations

    NgModule, veins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    es
    0.90
    in
    0.85
    an
    0.66
    p
    0.65
    as
    0.64
    y
    0.61
    g
    0.61
    ක්
    0.59
    yk
    0.59
    ing
    0.59
    POSITIVE LOGITS
     wrecked
    0.71
     supergiants
    0.65
     lured
    0.64
     vibrates
    0.63
     mascara
    0.62
     hatched
    0.62
     screws
    0.61
     outweighed
    0.61
    ڈین
    0.60
     skyrock
    0.60
    Act Density 0.000%

    No Known Activations