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

    Neuronpedia

    INDEX
    Explanations

    emojis and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AT
    0.84
    et
    0.79
    IAN
    0.73
    ON
    0.71
    tare
    0.70
    iul
    0.68
    ം
    0.68
    ET
    0.68
     underworld
    0.68
    ാന്‍
    0.67
    POSITIVE LOGITS
    1
    0.73
    ‍
    0.73
    你
    0.63
     मिलाकर
    0.61
     (\
    0.61
     (~
    0.60
     речи
    0.60
    that
    0.59
     that
    0.59
    ١
    0.57
    Act Density 0.000%

    No Known Activations