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

    Neuronpedia

    INDEX
    Explanations

    refusal of inappropriate requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    entar
    0.47
    ukaemia
    0.47
     '
    0.45
     Entropy
    0.42
     Euros
    0.42
     Lines
    0.41
     Ennis
    0.41
     euros
    0.41
     Opening
    0.41
     euro
    0.40
    POSITIVE LOGITS
     độ
    0.43
    தன்
    0.41
    लन
    0.41
    继承
    0.41
    登山
    0.41
     quân
    0.40
     gehe
    0.40
     ছোট
    0.40
     الذين
    0.40
    لس
    0.40
    Act Density 0.004%

    No Known Activations