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

    Neuronpedia

    INDEX
    Explanations

    your specific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.39
    或者
    0.39
    或者是
    0.38
     carburetor
    0.35
     buses
    0.34
     или
    0.34
    ಂಥ
    0.34
    LET
    0.33
     train
    0.33
     কিংবা
    0.33
    POSITIVE LOGITS
     akan
    0.39
    飥
    0.39
    ະ
    0.37
    恴
    0.36
    䐝
    0.35
    䚲
    0.35
    ළ
    0.35
     berkom
    0.34
     fokus
    0.34
    classe
    0.34
    Act Density 0.000%

    No Known Activations