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

    Neuronpedia

    INDEX
    Explanations

    references to tables in documents

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

    numbered tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.38
    sidemargin
    -0.37
     div
    -0.35
    rold
    -0.34
    XSSF
    -0.30
    mistic
    -0.30
    gros
    -0.30
     følge
    -0.30
     twist
    -0.29
    istic
    -0.28
    POSITIVE LOGITS
     otomatig
    0.62
     ब्रेकडाउन
    0.59
    клопе
    0.56
    terase
    0.52
    醐
    0.51
    Manbalar
    0.50
     Administrativna
    0.48
    ReusableCell
    0.48
    Personendaten
    0.47
    DMETHOD
    0.47
    Act Density 0.033%

    No Known Activations