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

    Neuronpedia

    INDEX
    Explanations

    support you or your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    其他
    0.58
     கட்டுர
    0.56
    ята
    0.55
     некоторы
    0.53
    。",
    0.50
     ಆದ್ದರಿಂದ
    0.50
     résult
    0.50
    োড
    0.49
     एडम
    0.49
     усі
    0.49
    POSITIVE LOGITS
     support
    0.92
     Support
    0.91
    یم
    0.87
    i
    0.86
    Support
    0.82
    ii
    0.79
    ach
    0.77
    ای
    0.77
    ill
    0.72
     सपोर्ट
    0.72
    Act Density 0.048%

    No Known Activations