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

    Neuronpedia

    INDEX
    Explanations

    attacks targeting, increasingly common

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     面
    0.48
     hooking
    0.45
    焲
    0.44
     bus
    0.43
     scones
    0.42
     assimil
    0.41
     Inverness
    0.41
     absorbing
    0.40
     solving
    0.40
    。（
    0.40
    POSITIVE LOGITS
    p
    0.48
    temper
    0.44
     இருக்கு
    0.44
     дій
    0.44
    ta
    0.43
    Include
    0.43
    Signed
    0.42
    ა
    0.42
    also
    0.42
    SEE
    0.42
    Act Density 0.001%

    No Known Activations