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

    Neuronpedia

    INDEX
    Explanations

    what's up followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeToFile
    0.42
    efois
    0.41
     পরিবার
    0.41
    cił
    0.40
    ൊപ്പം
    0.40
    remove
    0.40
    ️⃣
    0.40
     atop
    0.40
     gotta
    0.39
    slime
    0.39
    POSITIVE LOGITS
    학
    0.44
     angling
    0.43
    ancies
    0.41
    어
    0.41
    오늘
    0.40
    왕
    0.40
     girth
    0.39
    \
    0.39
    ย
    0.39
    ๑
    0.38
    Act Density 0.009%

    No Known Activations