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

    Neuronpedia

    INDEX
    Explanations

    foreign words and sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hadde
    0.73
     minify
    0.69
     역시
    0.69
    I
    0.68
     codon
    0.68
     मोटापा
    0.66
    মূলক
    0.66
     motivic
    0.65
     quisiera
    0.65
    🅘
    0.63
    POSITIVE LOGITS
    ة
    0.66
    ä
    0.54
     the
    0.52
     année
    0.52
    lycer
    0.52
     обстанов
    0.51
    าะ
    0.50
     conseguenza
    0.50
     élu
    0.50
     بالج
    0.50
    Act Density 0.000%

    No Known Activations