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

    Neuronpedia

    INDEX
    Explanations

    planning and goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rtList
    0.45
     delights
    0.40
    deltaTime
    0.39
    blockList
    0.39
    checked
    0.38
     mighty
    0.38
    بوط
    0.38
    ዎች
    0.37
    chées
    0.37
    ystone
    0.37
    POSITIVE LOGITS
    Sie
    0.46
     resorting
    0.41
     transplant
    0.40
     solvents
    0.39
     participação
    0.39
     coarse
    0.39
     Sieg
    0.38
     işlet
    0.38
     repatri
    0.37
     Describes
    0.37
    Act Density 0.001%

    No Known Activations