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

    Neuronpedia

    INDEX
    Explanations

    struct or class definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ை
    1.96
    ق
    1.89
    ์
    1.84
    కి
    1.76
    𝘆
    1.70
    сти
    1.67
     trwa
    1.66
    𝗲
    1.66
    Ngoài
    1.63
     eben
    1.61
    POSITIVE LOGITS
    о
    1.56
    ሰ
    1.55
    ering
    1.51
    tom
    1.49
     Lordships
    1.46
    midrule
    1.46
    a
    1.45
    Cancelar
    1.43
    onym
    1.43
     Percol
    1.40
    Act Density 0.004%

    No Known Activations