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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or number

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

    Quantifiers like "another", "few", "several"

    np_acts-logits-general · gemini-2.0-flash

    quantifiers and designations of others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     helicópter
    -0.53
    googleapis
    -0.47
    '));
    -0.45
     hjär
    -0.44
    riwal
    -0.44
     lèvres
    -0.43
     CreateTagHelper
    -0.43
     drapeau
    -0.42
     négociations
    -0.42
     {
    -0.41
    POSITIVE LOGITS
     ones
    1.10
     satunya
    0.77
     jScrollPane
    0.72
     Ones
    0.71
     delas
    0.67
     hers
    0.65
     theirs
    0.64
     виправивши
    0.63
     deles
    0.62
     others
    0.61
    Act Density 0.388%

    No Known Activations