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

    Neuronpedia

    INDEX
    Explanations

    fundamental concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     molte
    0.79
     ispod
    0.79
     विरुद्ध
    0.78
     priced
    0.78
     assorted
    0.76
    hasOwnProperty
    0.75
    Przyp
    0.75
    これで
    0.74
     desiring
    0.74
     diven
    0.73
    POSITIVE LOGITS
    ς
    0.75
     Какие
    0.73
    ﻧ
    0.69
    fem
    0.68
     درج
    0.67
    ು
    0.67
    aja
    0.66
    inschaft
    0.66
    ्यक्रम
    0.66
     Annotation
    0.65
    Act Density 0.000%

    No Known Activations