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

    Neuronpedia

    INDEX
    Explanations

    remnants of destruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mereka
    0.92
     因为
    0.88
     setDescription
    0.87
     posY
    0.87
     Porque
    0.87
     MessageBox
    0.85
     них
    0.85
     他们
    0.84
    נים
    0.84
     这些
    0.83
    POSITIVE LOGITS
    USA
    0.76
    perfect
    0.74
    ethnic
    0.73
     succès
    0.73
    quot
    0.72
    1
    0.71
    équ
    0.68
    citizen
    0.67
    honest
    0.67
    minute
    0.67
    Act Density 0.019%

    No Known Activations