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

    Neuronpedia

    INDEX
    Explanations

    numbered list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ibilités
    0.47
    тэ
    0.44
    ಾರ್ಟ
    0.44
    াহিয়া
    0.40
    ंगाई
    0.39
     tamaños
    0.38
    ująca
    0.38
    నాలను
    0.38
     assets
    0.38
    ̟
    0.37
    POSITIVE LOGITS
     Introduction
    0.57
     Understand
    0.52
     ≤
    0.49
     Create
    0.49
     Identify
    0.49
     Introduce
    0.48
     Einführung
    0.48
     Consider
    0.46
     Define
    0.46
     Identifying
    0.45
    Act Density 0.006%

    No Known Activations