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

    Neuronpedia

    INDEX
    Explanations

    tailor explanations or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nn
    0.47
    hile
    0.42
    Sing
    0.41
     поток
    0.41
    Eng
    0.41
    nEnter
    0.40
     redux
    0.40
     EUA
    0.40
     imediatamente
    0.40
    rda
    0.39
    POSITIVE LOGITS
     standardised
    0.47
     planters
    0.46
     산
    0.42
     ಮಾನ
    0.42
     campes
    0.42
    swadian
    0.42
     থাকিলেও
    0.42
     generalised
    0.40
     کاشت
    0.40
     permeability
    0.40
    Act Density 0.004%

    No Known Activations