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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to local and community-oriented actions or characteristics

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

    ending in "-ly," "-ally," or "-tically"

    np_acts-logits-general · gemini-2.0-flash

    adverbs ending in ly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    -0.54
    স্
    -0.53
    B
    -0.53
    b
    -0.50
    r
    -0.50
    ss
    -0.50
    in
    -0.49
    k
    -0.48
    1
    -0.48
    2
    -0.47
    POSITIVE LOGITS
     speaking
    0.99
     Yours
    0.96
     parlant
    0.94
     hablando
    0.91
    تقاوى
    0.87
    AddTagHelper
    0.85
    #
    0.85
     GenerationType
    0.83
     betweenstory
    0.83
     vôtre
    0.82
    Act Density 0.500%

    No Known Activations