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

    Neuronpedia

    INDEX
    Explanations

    refusing harmful story continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ót
    0.48
    🤟
    0.48
     आईपी
    0.43
     ಗ
    0.43
     ماں
    0.42
     గే
    0.41
     ഐ
    0.41
     bearbeitet
    0.41
    ೀರಿ
    0.41
    phthalm
    0.40
    POSITIVE LOGITS
    https
    0.49
    astikan
    0.46
    ה
    0.46
     completes
    0.45
    Kết
    0.44
     spinner
    0.43
    Selamat
    0.41
     kết
    0.41
    j
    0.41
     concludes
    0.40
    Act Density 0.001%

    No Known Activations