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

    Neuronpedia

    INDEX
    Explanations

    incredibly irresponsible dangerous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    0.48
    Sp
    0.48
    discount
    0.47
    O
    0.47
    tl
    0.46
    EL
    0.46
    of
    0.46
    Esp
    0.45
    Sos
    0.45
    on
    0.45
    POSITIVE LOGITS
     phenomenal
    0.46
    )>=
    0.45
     flash
    0.44
     frenzy
    0.43
     atmosphere
    0.43
     nightmares
    0.42
     cellophane
    0.42
     bulb
    0.42
     navbar
    0.41
     lacquer
    0.41
    Act Density 0.012%

    No Known Activations