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

    Neuronpedia

    INDEX
    Explanations

    The Economist Intelligence Unit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    0.66
    C
    0.61
    R
    0.55
    temperatur
    0.53
    G
    0.52
    ing
    0.51
    Crist
    0.51
    U
    0.51
     Teflon
    0.50
    Judy
    0.50
    POSITIVE LOGITS
    д
    0.64
     жив
    0.57
     leftWheel
    0.57
    儡
    0.55
     dõi
    0.53
     часу
    0.51
     расте
    0.48
     중에
    0.48
     леса
    0.47
     polvo
    0.47
    Act Density 0.000%

    No Known Activations