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

    Neuronpedia

    INDEX
    Explanations

    references to documents or research papers

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

    experimental study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.57
     ब्रेकडाउन
    -0.47
     kasarigan
    -0.45
    fromnode
    -0.44
     autorytatywna
    -0.42
    HtmlAttribute
    -0.41
     resourceCulture
    -0.39
    :✨
    -0.36
    '}),
    -0.36
    Pranala
    -0.36
    POSITIVE LOGITS
    bootstrapcdn
    0.59
     تضيفلها
    0.58
     defaultstate
    0.56
    .*")]
    0.53
    mtrl
    0.52
    ANTLR
    0.48
     AspNetCore
    0.48
    astéroïdes
    0.46
    laid
    0.46
     الحره
    0.45
    Act Density 0.039%

    No Known Activations