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

    Neuronpedia

    INDEX
    Explanations

    idle, talking, running, sleeping, casting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trigonometry
    0.42
     keyCode
    0.39
     fisica
    0.39
    硌
    0.38
     pengendalian
    0.38
    zechoslovakia
    0.37
    ={\
    0.37
    thebetterindia
    0.37
    TGFuZ
    0.37
    ቺ
    0.37
    POSITIVE LOGITS
     idle
    0.83
    idle
    0.75
     Idle
    0.74
    Idle
    0.71
     idling
    0.68
    闲
    0.63
    讲话
    0.51
    閒
    0.51
     Talking
    0.50
     quiescent
    0.50
    Act Density 0.008%

    No Known Activations