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

    Neuronpedia

    INDEX
    Explanations

    django framework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     milk
    0.66
     in
    0.65
     is
    0.64
    1
    0.62
     die
    0.59
     a
    0.58
    der
    0.58
    lle
    0.57
    lé
    0.57
     das
    0.57
    POSITIVE LOGITS
    Muchas
    0.64
    я
    0.63
    ᱐
    0.61
    ль
    0.60
    ̣ng
    0.59
     खबरें
    0.58
    セキュリティ
    0.57
    ння
    0.56
    реза
    0.56
    न्दगी
    0.56
    Act Density 0.001%

    No Known Activations