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

    Neuronpedia

    INDEX
    Explanations

    seeming, reporting, or alleged

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.32
    \
    0.30
    -
    0.30
    ：
    0.30
    URE
    0.29
    ，
    0.29
     ergonomics
    0.29
    :
    0.28
    RENGTH
    0.28
    ｜
    0.27
    POSITIVE LOGITS
     parecía
    0.49
     tampak
    0.46
     semblent
    0.43
     seemed
    0.43
     scheint
    0.42
    řejmě
    0.41
     reportedly
    0.41
     parecen
    0.39
     était
    0.39
     कथित
    0.39
    Act Density 0.000%

    No Known Activations