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

    Neuronpedia

    INDEX
    Explanations

    frog

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    า
    0.73
     về
    0.72
    asını
    0.63
     dân
    0.63
     diante
    0.63
     सूचित
    0.62
     தேர்தல்
    0.62
     स्थान
    0.61
     Electoral
    0.61
     định
    0.61
    POSITIVE LOGITS
    لي
    0.73
    SA
    0.70
    RI
    0.66
    TON
    0.64
    air
    0.64
    TE
    0.63
    2
    0.63
    B
    0.63
    ade
    0.61
    luft
    0.61
    Act Density 0.001%

    No Known Activations