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

    Neuronpedia

    INDEX
    Explanations

    to keep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expl
    0.39
     взгля
    0.37
     overload
    0.37
     tea
    0.36
     смотреть
    0.36
    BeanFactory
    0.36
     critically
    0.35
    拥
    0.35
     દિવસે
    0.35
    View
    0.34
    POSITIVE LOGITS
    íduos
    0.52
    翛
    0.47
    غه
    0.47
    醌
    0.45
     menutup
    0.43
    ׃
    0.43
     অভ্যন্তরীণ
    0.42
     URANIUM
    0.42
     kajian
    0.42
    溧
    0.41
    Act Density 0.000%

    No Known Activations