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

    Neuronpedia

    INDEX
    Explanations

    specific terms and phrases related to complex identifiers and classifications

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

    selection of features or forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.53
    AutoScale
    -0.36
     Roskov
    -0.36
     Wave
    -0.34
    Brainz
    -0.33
     need
    -0.32
     âgées
    -0.31
    ormal
    -0.31
     revanche
    -0.31
     devraient
    -0.31
    POSITIVE LOGITS
    astéro
    0.60
    GEBURTSDATUM
    0.59
     Мексичка
    0.56
     kasarigan
    0.53
    astéroïdes
    0.52
    sizeCache
    0.50
    EDEFAULT
    0.48
    tanleria
    0.46
     hochzeit
    0.46
    chowa
    0.46
    Act Density 0.002%

    No Known Activations