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

    Neuronpedia

    INDEX
    Explanations

    Times, sometimes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.46
     time
    0.44
     Speed
    0.44
     Time
    0.43
     ludicrous
    0.42
    Time
    0.41
     Tron
    0.41
     véritable
    0.40
    ి
    0.40
     velocity
    0.39
    POSITIVE LOGITS
     основе
    0.52
     современные
    0.49
     обычно
    0.47
     ഓ
    0.46
     வேண்டும்
    0.45
     большинство
    0.45
    лил
    0.44
     área
    0.43
    hare
    0.43
    rakt
    0.43
    Act Density 0.004%

    No Known Activations