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

    Neuronpedia

    INDEX
    Explanations

    data and professional contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fluff
    0.43
     있다는
    0.42
     Velcro
    0.40
    ahmatullahi
    0.40
    烪
    0.40
     போராட்ட
    0.39
     Cumbria
    0.39
     Uncle
    0.39
    🙎
    0.39
     Invention
    0.39
    POSITIVE LOGITS
    data
    0.43
    licenses
    0.43
     data
    0.42
    データを
    0.40
    سي
    0.39
     datap
    0.39
     third
    0.39
    Fra
    0.39
    3
    0.38
     datos
    0.38
    Act Density 10.488%

    No Known Activations