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

    Neuronpedia

    INDEX
    Explanations

    folklore narratives and cultural contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iciencia
    0.75
    anız
    0.74
    зать
    0.69
    ﻞ
    0.69
     escalera
    0.67
    د
    0.66
     monsieur
    0.65
    нды
    0.64
    ଇ
    0.64
    нің
    0.63
    POSITIVE LOGITS
     and
    0.75
     to
    0.74
    ist
    0.71
     in
    0.70
     or
    0.69
    ↵↵
    0.69
     are
    0.68
     व
    0.63
    m
    0.62
    and
    0.61
    Act Density 0.000%

    No Known Activations