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

    Neuronpedia

    INDEX
    Explanations

    appreciate you or being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acknowledge
    0.54
    acknowledge
    0.50
     acknowledges
    0.44
     respectfully
    0.44
     importância
    0.42
     सम्मान
    0.41
    importanza
    0.40
    かと思います
    0.40
     tradizione
    0.40
     commendable
    0.40
    POSITIVE LOGITS
    ត្រូវបាន
    0.45
    Known
    0.45
    被
    0.44
    MaxWidth
    0.44
    imme
    0.42
    ែ
    0.41
    េទ
    0.41
     being
    0.39
    EXE
    0.39
    EMY
    0.38
    Act Density 0.004%

    No Known Activations