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

    Neuronpedia

    INDEX
    Explanations

    email and web addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     প্রয
    0.40
     Activate
    0.40
     לת
    0.40
     되는
    0.39
     authorizes
    0.38
     authorize
    0.38
     ある
    0.38
     심
    0.38
     grup
    0.38
     criticize
    0.37
    POSITIVE LOGITS
    deviceId
    0.41
    ్రో
    0.41
    znak
    0.39
     wrecked
    0.39
    ภูมิ
    0.38
    ській
    0.38
     rou
    0.37
     Talon
    0.37
     device
    0.37
     yak
    0.37
    Act Density 0.001%

    No Known Activations