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

    Neuronpedia

    INDEX
    Explanations

    mathematical and foreign language terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    1.50
    ان
    1.29
    er
    1.27
    f
    1.16
    र
    1.12
    is
    1.11
    repo
    1.11
    e
    1.11
    erai
    1.09
    ன்
    1.08
    POSITIVE LOGITS
     háb
    0.97
     ゴルフ
    0.91
     linestyle
    0.89
     tämä
    0.88
    غب
    0.88
     findings
    0.87
     câte
    0.87
     Legendre
    0.87
     bús
    0.86
     leistungs
    0.86
    Act Density 0.001%

    No Known Activations