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

    Neuronpedia

    INDEX
    Explanations

    analysis and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.39
     DAB
    0.39
     JA
    0.38
     revolutionary
    0.38
     Firefox
    0.36
     revolucion
    0.36
     entusi
    0.35
     Jonathan
    0.35
     Swift
    0.35
     Stephen
    0.35
    POSITIVE LOGITS
    REAM
    0.48
     linge
    0.46
    BySize
    0.44
     Количество
    0.44
     মজুদ
    0.44
    📬
    0.44
     zależności
    0.43
    Autres
    0.43
     दाखल
    0.42
     bassin
    0.42
    Act Density 0.007%

    No Known Activations