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

    Neuronpedia

    INDEX
    Explanations

    measurement or analysis tool

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ඇත
    0.39
    新たに
    0.39
    values
    0.38
    šana
    0.38
     substances
    0.37
    அ
    0.37
     values
    0.36
     dėl
    0.36
     ona
    0.35
    Objects
    0.34
    POSITIVE LOGITS
     consulter
    0.36
    /
    0.34
     লিখ
    0.33
     รอบ
    0.33
    向けの
    0.33
    osha
    0.33
    ＆
    0.33
    ionista
    0.33
    েন্ট
    0.32
    颖
    0.32
    Act Density 0.104%

    No Known Activations