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

    Neuronpedia

    INDEX
    Explanations

    English, Spanish, French, Dutch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     collegamento
    0.94
     montaje
    0.92
     факторов
    0.91
     footnotes
    0.91
     veloce
    0.91
     нейтро
    0.89
    ックレス
    0.88
    zał
    0.87
     khá
    0.87
     glanced
    0.87
    POSITIVE LOGITS
    By
    0.87
    It
    0.87
    This
    0.85
    Do
    0.79
    स
    0.79
    FU
    0.78
    Just
    0.77
    The
    0.77
    For
    0.77
    Because
    0.75
    Act Density 0.000%

    No Known Activations