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

    Neuronpedia

    INDEX
    Explanations

    described as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )^{-
    0.52
     kontinu
    0.49
     दोन्ही
    0.49
     सीमित
    0.49
    jols
    0.48
    oglobin
    0.48
     Damit
    0.48
     しっかり
    0.47
     やっぱり
    0.46
     internationales
    0.45
    POSITIVE LOGITS
    Bug
    0.49
    Television
    0.48
    Work
    0.47
    Body
    0.47
    Andrew
    0.46
    Est
    0.46
    Concrete
    0.44
    UK
    0.44
    Inc
    0.44
    Beauty
    0.43
    Act Density 0.004%

    No Known Activations