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

    Neuronpedia

    INDEX
    Explanations

    chemical symbols and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۰۰
    2.08
    >
    1.45
    lenen
    1.40
    특별시
    1.39
    ","
    1.37
    traumatic
    1.37
    tage
    1.36
    েও
    1.36
    >$
    1.35
    tails
    1.34
    POSITIVE LOGITS
    ن
    2.97
    ك
    2.08
    س
    2.05
    на
    2.02
    et
    1.98
    ا
    1.97
    م
    1.95
    نن
    1.94
    ين
    1.91
    at
    1.87
    Act Density 0.486%

    No Known Activations