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

    Neuronpedia

    INDEX
    Explanations

    sending messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    もら
    0.96
    ionante
    0.87
    е
    0.85
    ak
    0.84
    ate
    0.83
    ian
    0.83
    inin
    0.82
    am
    0.81
    ot
    0.80
    も
    0.79
    POSITIVE LOGITS
     sends
    1.18
     send
    1.13
     sending
    1.13
     отправ
    1.07
     zacz
    1.07
     senden
    1.05
     envoyé
    1.04
    发送
    1.02
     भेजने
    1.01
     gửi
    0.98
    Act Density 0.081%

    No Known Activations