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

    Neuronpedia

    INDEX
    Explanations

    extract the word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ્વા
    0.75
     салы
    0.74
    o
    0.73
    0.71
    ру
    0.71
    των
    0.71
    හු
    0.71
    Hib
    0.71
    snacks
    0.69
    Mold
    0.69
    POSITIVE LOGITS
     número
    0.86
     temor
    0.83
     Paralympic
    0.83
     Número
    0.78
     difíc
    0.78
     passen
    0.78
     ganas
    0.76
     bună
    0.75
     tmux
    0.74
    ния
    0.74
    Act Density 0.000%

    No Known Activations