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

    Neuronpedia

    INDEX
    Explanations

    understand things; numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     differenti
    0.42
    ési
    0.40
     Coliseum
    0.39
     e
    0.38
     classified
    0.38
     Germania
    0.38
    ✪
    0.38
    asy
    0.37
    ાગ
    0.37
     everything
    0.37
    POSITIVE LOGITS
     Issled
    0.43
    чком
    0.42
     непосред
    0.39
    RoundRect
    0.39
    omores
    0.39
    Semif
    0.38
     නිර්
    0.38
    står
    0.38
     mẹ
    0.37
    getNumber
    0.37
    Act Density 0.000%

    No Known Activations