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

    Neuronpedia

    INDEX
    Explanations

    list delimiters or introductory words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erweise
    0.79
    n
    0.75
    numeric
    0.73
    ták
    0.72
    да
    0.71
    o
    0.71
    t
    0.70
    ্ডার
    0.69
    ions
    0.68
    tions
    0.66
    POSITIVE LOGITS
     tritium
    0.96
     mundial
    0.85
     peptid
    0.84
     fudai
    0.84
     prilikom
    0.83
     ridurre
    0.82
    दे
    0.81
     peruse
    0.81
    मौ
    0.80
     perjury
    0.80
    Act Density 0.000%

    No Known Activations