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

    Neuronpedia

    INDEX
    Explanations

    crisis support hotlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ehl
    0.65
    -/
    0.65
    oys
    0.63
     의
    0.62
    䄪
    0.62
     superconduct
    0.61
    fono
    0.61
    ベ
    0.61
    ిల్లా
    0.61
     topologically
    0.60
    POSITIVE LOGITS
    ਵ
    0.67
    情
    0.66
    這樣
    0.65
     свое
    0.64
     stun
    0.64
    遏
    0.63
    Shroud
    0.62
     heartbreaking
    0.62
     really
    0.60
    ൻ
    0.60
    Act Density 0.018%

    No Known Activations