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

    Neuronpedia

    INDEX
    Explanations

    audio experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    before
    0.37
    ंशी
    0.36
    umper
    0.36
     hybr
    0.36
    čním
    0.35
    berat
    0.35
     Carter
    0.35
    jou
    0.35
    whatever
    0.35
    丁
    0.34
    POSITIVE LOGITS
     dźwię
    0.56
     صوت
    0.55
     audio
    0.55
     sound
    0.52
     sonido
    0.51
     зву
    0.50
     Sound
    0.49
    音
    0.48
    Sound
    0.47
     звук
    0.46
    Act Density 0.000%

    No Known Activations