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

    Neuronpedia

    INDEX
    Explanations

    modified activity to return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ücks
    0.43
    Kü
    0.41
    Locked
    0.41
    Rectangle
    0.40
    ዥ
    0.39
    cue
    0.38
    Cue
    0.38
    찌
    0.38
    ToBounds
    0.37
    Wiki
    0.37
    POSITIVE LOGITS
     resuming
    0.70
     healing
    0.68
     light
    0.68
     resumption
    0.66
     ringan
    0.65
     conval
    0.63
     resumed
    0.62
     doctor
    0.61
     readiness
    0.61
     doctors
    0.60
    Act Density 0.009%

    No Known Activations