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

    Neuronpedia

    INDEX
    Explanations

    epistemic indeterminacy and existential threats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    0.61
    O
    0.59
    ى
    0.59
    ير
    0.58
    خ
    0.57
    عرف
    0.55
    ح
    0.55
    ط
    0.55
    ق
    0.54
    اخت
    0.53
    POSITIVE LOGITS
     Picnic
    0.52
     Palazzo
    0.50
    ંટણી
    0.50
    的市场
    0.50
    入れて
    0.48
     refundable
    0.47
    💶
    0.47
     Garnier
    0.47
     주변
    0.46
     सुनाई
    0.46
    Act Density 0.000%

    No Known Activations