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

    Neuronpedia

    INDEX
    Explanations

    default values or initializations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     použív
    0.47
     inconven
    0.43
     reluctantly
    0.43
     inasmuch
    0.42
     frequently
    0.41
     thêm
    0.40
     boleh
    0.39
     schimb
    0.39
     gás
    0.39
    巒
    0.39
    POSITIVE LOGITS
    Floral
    0.50
    Opera
    0.49
    Soon
    0.47
    Number
    0.45
    String
    0.45
     그리고
    0.45
    Derived
    0.45
     opere
    0.44
    Figures
    0.43
     نبی
    0.43
    Act Density 0.001%

    No Known Activations