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

    Neuronpedia

    INDEX
    Explanations

    words starting with specific sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ostante
    0.30
    mselves
    0.28
    çük
    0.28
    으로
    0.28
    voorbeeld
    0.27
    chließlich
    0.27
    해서
    0.27
    şağı
    0.27
    ervlak
    0.27
    加坡
    0.26
    POSITIVE LOGITS
    ophilic
    0.31
    undering
    0.30
    attering
    0.29
     menacing
    0.28
     sobbing
    0.27
    aphthal
    0.27
    ousing
    0.27
     inept
    0.27
    dometer
    0.27
    owness
    0.26
    Act Density 0.305%

    No Known Activations