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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agy
    0.45
     Rainbow
    0.42
    ancs
    0.42
    one
    0.42
    的一次
    0.41
     Creative
    0.41
     داستان
    0.41
    зки
    0.41
    वन
    0.40
     Geschichten
    0.40
    POSITIVE LOGITS
    ändert
    0.47
    ishly
    0.47
    语气
    0.46
     اريد
    0.45
     overrides
    0.45
     infest
    0.44
    鰥
    0.44
     jeopard
    0.43
     ellipt
    0.43
     regulates
    0.43
    Act Density 0.002%

    No Known Activations