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

    Neuronpedia

    INDEX
    Explanations

    suggestions & instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onen
    0.54
    van
    0.53
    um
    0.52
    ian
    0.50
    vis
    0.50
     だ
    0.50
    Forever
    0.50
    has
    0.50
    mond
    0.49
    ism
    0.48
    POSITIVE LOGITS
    ي
    0.59
    י
    0.47
     Kwiatkowski
    0.46
     applic
    0.46
     pests
    0.45
    ۔
    0.45
    س
    0.45
     railings
    0.44
    ப்பது
    0.44
    ನ
    0.44
    Act Density 0.000%

    No Known Activations