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

    Neuronpedia

    INDEX
    Explanations

    Valkyrie, Akira, Rainbow Dash, Orb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਰ
    0.56
    ीडी
    0.49
    ing
    0.48
     fuente
    0.48
     besser
    0.47
     diamante
    0.47
    ugh
    0.47
    ล
    0.47
     Notas
    0.46
     rays
    0.46
    POSITIVE LOGITS
     <
    0.50
     ७
    0.50
     Վ
    0.50
     Β
    0.47
    ف
    0.46
    '
    0.45
     مؤرشف
    0.44
     बाळा
    0.44
     Ө
    0.44
     Î
    0.43
    Act Density 0.025%

    No Known Activations