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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to easy interactions or one-click processes

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

    single click action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.62
    webElementXpaths
    -0.54
    ruptedException
    -0.54
     المعيارى
    -0.50
    principalTable
    -0.49
    basicConfig
    -0.46
     GenerationType
    -0.46
    帖最后由
    -0.45
    Життєпис
    -0.45
    évaluateur
    -0.44
    POSITIVE LOGITS
     instantly
    0.54
     effortlessly
    0.49
     snap
    0.45
     instantaneously
    0.44
     effortless
    0.44
     Instantly
    0.44
    immediate
    0.44
    easily
    0.43
     click
    0.42
     easy
    0.41
    Act Density 0.017%

    No Known Activations