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

    Neuronpedia

    INDEX
    Explanations

    Drake Equation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emphasizes
    0.48
     combines
    0.42
    roscopic
    0.41
    libc
    0.40
     emphasises
    0.40
     emphasize
    0.39
     emphasis
    0.38
     emphasized
    0.38
    ciu
    0.38
     исключительно
    0.38
    POSITIVE LOGITS
     formula
    0.62
     fórmula
    0.61
     формула
    0.60
     Formula
    0.52
    formula
    0.51
    Formula
    0.50
     formule
    0.50
     Fórmula
    0.49
     whereby
    0.49
     তাতে
    0.47
    Act Density 0.000%

    No Known Activations