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

    Neuronpedia

    INDEX
    Explanations

    reset, clear, angle, defy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bevat
    0.54
    يف
    0.52
     führen
    0.50
     ge
    0.48
     Conce
    0.47
    中文
    0.47
    تع
    0.47
     الع
    0.46
     internas
    0.46
     Re
    0.46
    POSITIVE LOGITS
    neurons
    0.58
    soldiers
    0.58
    सर्गिक
    0.55
    amyl
    0.54
    ow
    0.53
     seedlings
    0.53
     strolled
    0.53
    slow
    0.52
     vultures
    0.52
    sliced
    0.52
    Act Density 0.002%

    No Known Activations