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

    Neuronpedia

    INDEX
    Explanations

    structures and syntax used in mathematical notation

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

    LaTeX array environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tampoco
    -0.38
     liksom
    -0.38
     tamén
    -0.36
     незавершена
    -0.35
    Kaynakça
    -0.34
    ficado
    -0.34
    ########.
    -0.34
    mml
    -0.33
    eadilan
    -0.33
     berarti
    -0.33
    POSITIVE LOGITS
    mtable
    0.99
    array
    0.95
     array
    0.69
    arrays
    0.62
     GenerationType
    0.60
     Arrays
    0.57
     arrays
    0.57
    0.55
    xymatrix
    0.54
    ContentAlignment
    0.54
    Act Density 0.046%

    No Known Activations