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

    Neuronpedia

    INDEX
    Explanations

    cancellation policy or fee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vendeur
    0.43
     probablement
    0.43
    護
    0.43
    =========
    0.41
    หาคม
    0.41
    うまく
    0.40
     সম্ভবত
    0.39
     destaca
    0.39
     Тут
    0.39
     downsides
    0.39
    POSITIVE LOGITS
     ALL
    0.48
    onski
    0.44
     Failure
    0.43
    Failure
    0.42
    及时
    0.42
     Factors
    0.42
     missed
    0.41
     Unless
    0.41
     Allergy
    0.41
    Miss
    0.41
    Act Density 0.020%

    No Known Activations