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

    Neuronpedia

    INDEX
    Explanations

    out of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mechanism
    0.37
     Mechanism
    0.36
     വേണ്ട
    0.36
     domest
    0.35
     механизм
    0.34
    PR
    0.34
     mechanism
    0.34
    дони
    0.33
     ግ
    0.32
     પ્રાપ્ત
    0.32
    POSITIVE LOGITS
     of
    0.64
     ofthe
    0.61
    ของการ
    0.48
    ของ
    0.47
     của
    0.43
     ऑफ
    0.40
    ofthe
    0.39
    lays
    0.39
     hereof
    0.39
    OfString
    0.38
    Act Density 0.008%

    No Known Activations