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

    Neuronpedia

    INDEX
    Explanations

    Super AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াচিত
    0.78
     Pentland
    0.74
     losing
    0.73
    衽
    0.72
    urations
    0.70
     west
    0.69
    mila
    0.69
    меры
    0.69
     fnt
    0.68
    iterations
    0.68
    POSITIVE LOGITS
    خب
    0.69
    িয়া
    0.67
     कारखाना
    0.66
    幺
    0.65
     Shall
    0.63
     Ads
    0.63
     Fact
    0.63
     Services
    0.63
    षा
    0.63
    ജി
    0.62
    Act Density 0.004%

    No Known Activations