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

    Neuronpedia

    INDEX
    Explanations

    greeting jokes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.98
    7
    0.84
    6
    0.83
    <0x18>
    0.81
    8
    0.80
     testAvg
    0.78
    Б
    0.78
    cellSize
    0.78
    Су
    0.77
    Г
    0.76
    POSITIVE LOGITS
     infarction
    0.85
    itionally
    0.82
     didn
    0.79
     pornography
    0.78
     marketing
    0.76
     납
    0.76
     ves
    0.75
     postgraduate
    0.75
    ified
    0.74
     dishonesty
    0.73
    Act Density 0.000%

    No Known Activations