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

    Neuronpedia

    INDEX
    Explanations

    phrases that pertain to actions and connections within a subject

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

    html tags, code, and sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.84
    الدراسه
    -0.77
     Waſſer
    -0.74
     مرئيه
    -0.73
    المناصب
    -0.72
     ſelbſt
    -0.70
     esternos
    -0.70
     ſehr
    -0.69
    󠁣
    -0.69
     kaarangay
    -0.68
    POSITIVE LOGITS
    .
    0.40
    <h1>
    0.40
     that
    0.37
    <h2>
    0.36
     it
    0.35
    it
    0.34
    The
    0.33
    (
    0.33
    hObject
    0.33
    <h3>
    0.32
    Act Density 0.128%

    No Known Activations