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

    Neuronpedia

    INDEX
    Explanations

    references to societal judgments and the moral implications of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    towards specific outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.66
     nakalista
    -0.53
    Hozzáférés
    -0.50
     surla
    -0.48
    下载附件
    -0.47
     متعلقه
    -0.44
     inform
    -0.43
     InputDecoration
    -0.43
     Audiodateien
    -0.42
    Launched
    -0.41
    POSITIVE LOGITS
    もしか
    0.45
    RTSN
    0.44
    OCCURRED
    0.41
    jiny
    0.40
     المعيارى
    0.40
    openzeppelin
    0.40
    ussis
    0.38
    EDEFAULT
    0.37
     otomatig
    0.36
    right
    0.36
    Act Density 0.072%

    No Known Activations