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

    Neuronpedia

    INDEX
    Explanations

    simulate understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ouncement
    0.41
    Util
    0.39
    veston
    0.39
     tempList
    0.39
    僄
    0.39
    ⚊
    0.39
     menuMobile
    0.38
     inputRange
    0.38
     intimidation
    0.38
     Completely
    0.38
    POSITIVE LOGITS
     dutiful
    0.75
     faithfully
    0.67
     plaus
    0.61
     reliably
    0.60
     exquisitely
    0.59
     regurg
    0.54
     mimic
    0.53
     cheerfully
    0.53
     mim
    0.52
     obedient
    0.51
    Act Density 0.063%

    No Known Activations