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

    Neuronpedia

    INDEX
    Explanations

    easy to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     concernant
    0.57
     possibilité
    0.57
     daripada
    0.56
    ፣
    0.54
     retten
    0.52
    不久
    0.52
     ochron
    0.52
     intéressant
    0.51
     révé
    0.51
    ut
    0.51
    POSITIVE LOGITS
    く
    0.60
    ד
    0.60
    س
    0.57
    وت
    0.55
    و
    0.52
    د
    0.52
    ز
    0.52
    С
    0.52
    liest
    0.51
    ット
    0.50
    Act Density 0.777%

    No Known Activations