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

    Neuronpedia

    INDEX
    Explanations

    wearing pajamas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝟬
    0.68
    תו
    0.61
    ;
    0.59
    ン
    0.59
    0
    0.57
    ktu
    0.56
    of
    0.54
    ﻠ
    0.54
     kuru
    0.52
    지
    0.52
    POSITIVE LOGITS
    makarna
    0.55
    на
    0.54
     উন্নয়ন
    0.54
    婜
    0.53
     over
    0.52
     Choisissez
    0.52
    нодоро
    0.51
     Sverige
    0.50
    ্জন
    0.50
    ня
    0.50
    Act Density 0.000%

    No Known Activations