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

    Neuronpedia

    INDEX
    Explanations

    specific topics or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ികി
    0.46
     huh
    0.46
     знаю
    0.46
     Neurosci
    0.43
    자의
    0.43
     lexicon
    0.42
    ٨
    0.41
     kini
    0.40
     linguistics
    0.40
    alker
    0.40
    POSITIVE LOGITS
    徝
    0.44
     entsteht
    0.42
    reeks
    0.41
    哚
    0.40
    ION
    0.39
     entstehen
    0.39
    స్తాయి
    0.39
    λάβ
    0.39
    সং
    0.39
    ině
    0.39
    Act Density 0.000%

    No Known Activations