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

    Neuronpedia

    INDEX
    Explanations

    known for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dem
    0.67
     feedback
    0.66
    <h1>
    0.66
     i
    0.65
     them
    0.64
     lược
    0.64
     dis
    0.64
     disc
    0.64
     a
    0.63
     mind
    0.63
    POSITIVE LOGITS
    чин
    1.02
    opencamer
    0.93
     Mixtures
    0.92
    OGRAPHY
    0.92
    icosa
    0.92
    swear
    0.92
    ologne
    0.92
     BusABC
    0.92
    முகச்
    0.92
    числения
    0.91
    Act Density 0.127%

    No Known Activations