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

    Neuronpedia

    INDEX
    Explanations

    your audience and motivation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pozitiv
    0.46
    烷
    0.45
     htob
    0.42
     interface
    0.40
     crossings
    0.40
    人工智能
    0.39
    堝
    0.39
     cheeses
    0.39
     ಇದೆ
    0.39
     Vegan
    0.39
    POSITIVE LOGITS
    ילה
    0.45
    gning
    0.41
     fama
    0.41
    awning
    0.40
    वाले
    0.40
     அதற்கு
    0.39
    gare
    0.39
    书记
    0.38
     Fáb
    0.38
    ⑤
    0.38
    Act Density 0.001%

    No Known Activations