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

    Neuronpedia

    INDEX
    Explanations

    also or too

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     highly
    0.43
    டுகளை
    0.40
    就像
    0.39
     build
    0.38
    ಮಗೆ
    0.36
     എന്നാൽ
    0.36
     mı
    0.35
    sed
    0.34
     großer
    0.34
     quam
    0.34
    POSITIVE LOGITS
     тоже
    3.25
     भी
    3.05
     بھی
    2.92
     också
    2.84
     también
    2.78
     also
    2.77
     également
    2.77
     ebenfalls
    2.70
     também
    2.67
     også
    2.66
    Act Density 0.096%

    No Known Activations