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

    Neuronpedia

    INDEX
    Explanations

    each/every item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    حيان
    0.38
     Leute
    0.37
     are
    0.36
    ymptoms
    0.36
     allgemein
    0.36
    ulnerable
    0.35
     ہیں۔
    0.34
    ジャン
    0.34
    iggio
    0.34
    ехали
    0.34
    POSITIVE LOGITS
     individually
    0.78
     imaginable
    0.73
    마다
    0.69
     separately
    0.69
     ஒவ்வ
    0.66
     وكل
    0.61
     каждой
    0.60
    individ
    0.60
    Each
    0.58
     each
    0.57
    Act Density 0.066%

    No Known Activations