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

    Neuronpedia

    INDEX
    Explanations

    AliExpress product details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JU
    0.53
    :*
    0.50
    さんも
    0.50
    \*
    0.49
     bodily
    0.49
     postpone
    0.47
     depart
    0.46
     IU
    0.46
    **
    0.46
     GU
    0.46
    POSITIVE LOGITS
     بنانے
    0.52
    。「
    0.51
    顫
    0.51
     राजवंश
    0.51
    గి
    0.50
    ке
    0.49
    र्सन
    0.49
     ვერ
    0.49
     პრო
    0.49
    पुरम
    0.49
    Act Density 0.001%

    No Known Activations