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

    Neuronpedia

    INDEX
    Explanations

    cartilage damage or regeneration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    0.73
    ם
    0.69
    ،
    0.59
    ב
    0.57
    к
    0.56
    ک
    0.56
    ่า
    0.55
    ール
    0.54
    ம்ம
    0.54
    ف
    0.54
    POSITIVE LOGITS
    αν
    0.71
     Puedes
    0.70
    t
    0.69
     Sólo
    0.68
     будь
    0.67
     使っ
    0.66
     Tenemos
    0.65
     keď
    0.65
     reine
    0.64
    衄
    0.64
    Act Density 0.002%

    No Known Activations