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

    Neuronpedia

    INDEX
    Explanations

    LaTeX document preamble

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лизация
    0.43
    ifiée
    0.38
     насы
    0.38
    Scopes
    0.35
    င့်
    0.35
    🥱
    0.35
    ffekt
    0.34
    ┘
    0.34
    личи
    0.34
    ahul
    0.34
    POSITIVE LOGITS
    nummer
    0.43
    amsmath
    0.40
    numbers
    0.38
     roundup
    0.38
     nook
    0.38
    convert
    0.37
     twins
    0.37
     journal
    0.37
    border
    0.37
     epub
    0.37
    Act Density 0.001%

    No Known Activations