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

    Neuronpedia

    INDEX
    Explanations

    concepts related to common sense and intuitive reasoning

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

    intuition and common sense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Spécification
    -0.38
     CreateTagHelper
    -0.37
     ergeben
    -0.35
    +#+#
    -0.35
     ModelExpression
    -0.35
     posibilidades
    -0.35
     dança
    -0.34
     possibilités
    -0.33
    findpost
    -0.33
     gamis
    -0.32
    POSITIVE LOGITS
     intuiti
    0.55
    addCriterion
    0.55
     daglig
    0.51
     colloquial
    0.51
     snippetHide
    0.50
    AsUp
    0.50
     ControllerBase
    0.50
    webElementXpaths
    0.50
     fallu
    0.49
    省市镇
    0.48
    Act Density 0.251%

    No Known Activations