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

    Neuronpedia

    INDEX
    Explanations

    programming resources

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KSprite
    0.41
    tela
    0.38
    Nat
    0.38
    ッサージ
    0.38
     মাস্টার
    0.37
    শকার
    0.37
     chargingStation
    0.36
    썬
    0.36
    版
    0.36
     কল
    0.35
    POSITIVE LOGITS
     pattern
    0.47
     extreme
    0.41
     pity
    0.40
     h
    0.39
     spoiled
    0.39
     programme
    0.38
     주어진
    0.37
    ▇
    0.37
     given
    0.36
     mixed
    0.36
    Act Density 0.000%

    No Known Activations