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

    Neuronpedia

    INDEX
    Explanations

    code identifiers and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⁷
    0.65
     apparent
    0.64
     Παν
    0.63
     sieben
    0.62
     VII
    0.61
     seven
    0.59
     vii
    0.59
     ADR
    0.58
     Ker
    0.57
     criticized
    0.55
    POSITIVE LOGITS
    1.00
        
    0.90
     desarrollada
    0.73
    ziła
    0.73
    rières
    0.70
    关键字
    0.70
    zyła
    0.68
     ዓይ
    0.68
    organiser
    0.67
     LoggerFactory
    0.66
    Act Density 0.067%

    No Known Activations