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

    Neuronpedia

    INDEX
    Explanations

    sections, stages, sites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prestations
    0.45
    าร์
    0.44
    lectoral
    0.44
    นั้น
    0.42
     என்பவர்
    0.41
    िशन
    0.40
    itteln
    0.40
    ะ
    0.40
     bottles
    0.39
     shootings
    0.39
    POSITIVE LOGITS
     Ane
    0.47
    Pair
    0.46
    Ane
    0.45
     Phong
    0.43
     Góc
    0.42
    Phong
    0.42
     góc
    0.41
    Pham
    0.41
    Tôi
    0.40
    •
    0.40
    Act Density 0.012%

    No Known Activations