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

    Neuronpedia

    INDEX
    Explanations

    legal and privacy advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     জাতীয়
    0.50
    氫
    0.49
     స్థాయి
    0.47
    ై
    0.44
     জাতীয়
    0.44
     পতিত
    0.44
    參数
    0.44
     బ్యాం
    0.43
     পর্যায়ে
    0.43
     प्रयास
    0.42
    POSITIVE LOGITS
    in
    0.48
    January
    0.46
    ritte
    0.45
    ".[
    0.44
    \".
    0.43
    coin
    0.42
    ".
    0.40
    more
    0.40
    aining
    0.40
    PAGE
    0.40
    Act Density 0.004%

    No Known Activations