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

    Neuronpedia

    INDEX
    Explanations

    project configuration keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的游戏
    0.68
     défini
    0.66
    та
    0.64
     Então
    0.63
    郄
    0.63
    Então
    0.62
     géographique
    0.62
    érée
    0.60
     येथे
    0.59
     doença
    0.59
    POSITIVE LOGITS
    н
    0.75
     upheaval
    0.63
    in
    0.59
    ang
    0.59
     ette
    0.58
    n
    0.58
    1
    0.57
    int
    0.55
    ina
    0.55
    new
    0.55
    Act Density 0.001%

    No Known Activations