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

    Neuronpedia

    INDEX
    Explanations

    journal citation numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鄒
    0.42
    Попис
    0.40
    鿉
    0.40
     Bont
    0.37
    ्यूशन
    0.37
     ਤੇ
    0.37
     দূতাবাসের
    0.37
    Ри
    0.36
    станов
    0.36
    Euph
    0.36
    POSITIVE LOGITS
    sequ
    0.44
    ishop
    0.40
     sequel
    0.37
    őr
    0.35
    rd
    0.34
    hier
    0.34
    ossil
    0.33
     Nong
    0.33
    own
    0.33
    registerTask
    0.33
    Act Density 0.002%

    No Known Activations