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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or doubt

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

    adverbs of degree or certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.43
    DeleteMapping
    -0.40
     gardening
    -0.38
    removeAttr
    -0.37
     Manufact
    -0.36
     lacing
    -0.36
     racing
    -0.36
     funding
    -0.35
     is
    -0.34
     raving
    -0.34
    POSITIVE LOGITS
    yntaxException
    0.69
    وانید
    0.54
    parsedMessage
    0.50
    還可以
    0.45
    basicConfig
    0.45
     puedo
    0.45
     hâte
    0.45
    Podemos
    0.44
    Cannot
    0.44
    roughly
    0.44
    Act Density 0.014%

    No Known Activations