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

    Neuronpedia

    INDEX
    Explanations

    dispatching items or information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ak
    0.63
    soluble
    0.60
    ać
    0.56
    akty
    0.56
     in
    0.54
    在
    0.52
    ace
    0.51
    า
    0.51
    itation
    0.50
    ิน
    0.50
    POSITIVE LOGITS
     send
    1.13
     sending
    1.09
     Sending
    1.08
     envoyé
    1.07
     sends
    1.06
    Sending
    1.05
     gönder
    1.05
     भेज
    1.05
     보내
    1.04
     посы
    1.04
    Act Density 0.036%

    No Known Activations