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

    Neuronpedia

    INDEX
    Explanations

    elements, fruits, and flowers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    or
    1.18
     CMakeFiles
    1.05
    ни
    1.04
    માંથી
    1.02
    椑
    1.02
    ৪
    1.02
     কিন্ত
    1.00
     nightmares
    0.98
    או
    0.97
    and
    0.95
    POSITIVE LOGITS
    нда
    1.48
    т
    1.38
    ます
    1.27
    бо
    1.21
    кту
    1.20
    VITY
    1.18
    EXAMPLES
    1.16
    ς
    1.16
    platin
    1.14
    PAR
    1.12
    Act Density 0.219%

    No Known Activations