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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and warnings before proceeding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    මක්
    0.77
     a
    0.75
     the
    0.74
     jednego
    0.71
     an
    0.68
    方法
    0.64
    ăzi
    0.64
     foolproof
    0.62
    Method
    0.59
     във
    0.59
    POSITIVE LOGITS
     (“
    0.78
    .“
    0.77
    .].
    0.76
    ‌.
    0.74
     และ
    0.71
     and
    0.71
    .”
    0.70
     because
    0.69
     ஆகிய
    0.69
    iousness
    0.69
    Act Density 0.013%

    No Known Activations