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

    Neuronpedia

    INDEX
    Explanations

    `GeneratedValue` in code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    1.70
    िक
    1.66
     doe
    1.61
     Schrift
    1.58
    ни
    1.56
    čni
    1.51
    ﻖ
    1.50
    чин
    1.47
     люб
    1.46
     فعل
    1.45
    POSITIVE LOGITS
     "{{
    1.74
    '>";
    1.73
    '/
    1.67
    '}$
    1.67
    𝓊
    1.63
    𝓂
    1.62
     lige
    1.60
     तिथे
    1.57
    𝓀
    1.56
     राजकीय
    1.56
    Act Density 0.000%

    No Known Activations