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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zy
    0.74
    ukary
    0.73
     prolog
    0.72
    äle
    0.70
    丞
    0.70
    काई
    0.69
    tty
    0.69
     multicast
    0.69
    দেশের
    0.69
     blast
    0.68
    POSITIVE LOGITS
    まあ
    0.85
    grains
    0.76
    effort
    0.76
     당
    0.74
     예를
    0.73
     관
    0.72
    micro
    0.72
    solutions
    0.71
    grain
    0.71
     Mé
    0.70
    Act Density 0.000%

    No Known Activations