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

    Neuronpedia

    INDEX
    Explanations

    ** followed by points or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.51
    fini
    0.50
    綃
    0.46
    ga
    0.46
    erin
    0.46
    re
    0.44
    knit
    0.44
    leding
    0.43
     Londres
    0.42
    paris
    0.42
    POSITIVE LOGITS
    К
    0.47
    성
    0.44
    }")
    0.44
    avourable
    0.44
    บริการ
    0.44
    $)$.
    0.44
     punctato
    0.44
    С
    0.43
    Про
    0.42
    OfInterest
    0.42
    Act Density 0.019%

    No Known Activations