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

    Neuronpedia

    INDEX
    Explanations

    messages for otp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ވަ
    0.51
    боров
    0.48
    هما
    0.47
    nisse
    0.47
     representatives
    0.47
     poles
    0.46
    次の
    0.45
     proponents
    0.44
     distribute
    0.43
     artistas
    0.43
    POSITIVE LOGITS
     नं
    0.48
    erd
    0.47
    aretro
    0.46
    álogo
    0.45
     எண்
    0.45
    传入
    0.43
    rait
    0.42
     अर्जित
    0.42
    }}+\
    0.41
    ಾನೆ
    0.41
    Act Density 0.002%

    No Known Activations