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

    Neuronpedia

    INDEX
    Explanations

    start_of_turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    痛
    0.47
     torque
    0.41
    真人
    0.41
    不
    0.41
     simul
    0.39
    ुष
    0.39
     leads
    0.38
    িস
    0.38
    和
    0.38
    窒
    0.38
    POSITIVE LOGITS
     estadounid
    0.53
     Dunia
    0.52
     США
    0.49
     ola
    0.49
     Outer
    0.48
     SBT
    0.48
     SERIAL
    0.48
     वनस्प
    0.47
     świata
    0.47
     다운
    0.47
    Act Density 0.002%

    No Known Activations