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

    Neuronpedia

    INDEX
    Explanations

    persistence and cycles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ছাই
    0.61
    по
    0.58
     Jenis
    0.57
     Dens
    0.57
    ور
    0.55
     Felder
    0.55
    0.54
     including
    0.54
     Excuse
    0.53
    包括
    0.52
    POSITIVE LOGITS
     cambiamento
    0.69
     wrongdoing
    0.67
     lapses
    0.64
    recurring
    0.64
     recurrence
    0.63
    あるいは
    0.63
     benessere
    0.63
    ؤس
    0.63
    patterns
    0.62
     scarring
    0.62
    Act Density 0.013%

    No Known Activations