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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data or characteristics in a statistical context

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

    reporting statistics and demographics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etc
    -0.42
    providedIn
    -0.40
    etc
    -0.39
    GOTREF
    -0.37
    nością
    -0.34
     fermés
    -0.34
     consuming
    -0.32
     définiti
    -0.32
    pushFollow
    -0.32
    <eos>
    -0.31
    POSITIVE LOGITS
    abestanden
    0.62
    ParallelGroup
    0.58
     Offisielt
    0.58
    ValueStyle
    0.57
     تضيفلها
    0.57
    LabelTagHelper
    0.56
    hluk
    0.56
    setof
    0.56
    posedge
    0.55
    KommentareTeilen
    0.53
    Act Density 0.026%

    No Known Activations