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

    Neuronpedia

    INDEX
    Explanations

    estimating likelihoods for specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isEmpty
    0.44
    ້ອ
    0.42
     myocard
    0.42
     anatomic
    0.41
    ჲ
    0.41
    问道
    0.40
    黟
    0.40
     cran
    0.40
     قنات
    0.39
     planilla
    0.39
    POSITIVE LOGITS
    Ste
    0.49
    Free
    0.47
    free
    0.45
    All
    0.44
    Å
    0.44
    N
    0.44
    What
    0.42
    Best
    0.42
    Bad
    0.41
    F
    0.41
    Act Density 0.000%

    No Known Activations