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

    Neuronpedia

    INDEX
    Explanations

    positive qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ことにより
    0.46
    ش
    0.46
     gill
    0.44
     comply
    0.42
    extras
    0.41
    ăţ
    0.41
    對
    0.41
    :
    0.40
    وقف
    0.39
    hle
    0.39
    POSITIVE LOGITS
     仕事
    0.51
     स्पोर्ट
    0.44
     पादुकोण
    0.44
     आपण
    0.44
     capacitive
    0.43
     ވަ
    0.43
     Матери
    0.42
     auguri
    0.42
     이슈
    0.42
     آباد
    0.42
    Act Density 0.002%

    No Known Activations