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

    Neuronpedia

    INDEX
    Explanations

    especially around gas giants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    荪
    0.44
    度が
    0.41
     הספר
    0.41
     arcs
    0.40
     Weed
    0.39
     Sagittarius
    0.39
    ㅡ
    0.39
    ]",
    0.39
     witnessing
    0.38
     OCR
    0.38
    POSITIVE LOGITS
    जीत
    0.48
    ريع
    0.46
    خواست
    0.46
    ل
    0.46
    مد
    0.45
    اء
    0.45
    leck
    0.45
    lauf
    0.44
     expectativas
    0.44
    خوا
    0.43
    Act Density 0.002%

    No Known Activations