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

    Neuronpedia

    INDEX
    Explanations

    disclaimer or redirect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adiabatic
    0.45
     Gordo
    0.42
    ơi
    0.41
     Mord
    0.40
    盛り
    0.39
     adiabatically
    0.39
    Sal
    0.38
     salic
    0.38
     incremento
    0.38
     üçün
    0.38
    POSITIVE LOGITS
     https
    0.39
     เท
    0.38
     www
    0.37
     الكت
    0.36
    ﮟ
    0.36
     //
    0.36
     strtoupper
    0.35
    ativas
    0.35
     棉
    0.35
     mini
    0.34
    Act Density 0.013%

    No Known Activations