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

    Neuronpedia

    INDEX
    Explanations

    explaining consequence or condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    િ
    0.89
    א
    0.89
    ような
    0.88
     tire
    0.87
     shawl
    0.85
    раў
    0.84
     टायर
    0.84
     resin
    0.83
     нашего
    0.83
     anyway
    0.82
    POSITIVE LOGITS
     Parece
    0.88
    رک
    0.85
     Destination
    0.85
     Schalt
    0.84
     obtiene
    0.82
    stairs
    0.82
     XC
    0.82
     убы
    0.79
     Конечно
    0.77
    isons
    0.77
    Act Density 0.000%

    No Known Activations