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

    Neuronpedia

    INDEX
    Explanations

    commands and data formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ejemplo
    0.31
     bijvoorbeeld
    0.31
     aluminium
    0.30
     principi
    0.30
    пример
    0.29
     простой
    0.29
    example
    0.29
    ساس
    0.29
     Beispiel
    0.29
     orthodontic
    0.29
    POSITIVE LOGITS
     thời
    0.33
     submissions
    0.33
     submits
    0.30
    ycji
    0.30
     batches
    0.29
    ");
    0.29
     miejscowości
    0.29
    zeptember
    0.28
     images
    0.28
     decks
    0.28
    Act Density 0.205%

    No Known Activations