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

    Neuronpedia

    INDEX
    Explanations

    multi script characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    客様
    2.22
    𝘪
    2.22
    i
    1.99
    РА
    1.98
    ように
    1.95
    𝘻
    1.93
    که
    1.90
    적인
    1.85
    ه
    1.85
    ে
    1.84
    POSITIVE LOGITS
    ار
    2.53
    re
    2.13
    ра
    2.02
    ד
    1.92
    de
    1.88
    så
    1.85
    san
    1.83
    ان
    1.76
    ről
    1.74
    च्या
    1.72
    Act Density 0.026%

    No Known Activations