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

    Neuronpedia

    INDEX
    Explanations

    The Trevor Project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    www
    1.01
     www
    0.95
     ignore
    0.92
     puissiez
    0.90
     haver
    0.89
     avoiding
    0.88
    稼
    0.88
     ignoring
    0.87
     deven
    0.85
    rarr
    0.84
    POSITIVE LOGITS
    ণ
    0.96
     تامین
    0.93
     convertView
    0.88
    <0xA7>
    0.87
    ية
    0.87
    wave
    0.86
     bombe
    0.83
     бан
    0.83
    <0xA1>
    0.83
     فکر
    0.82
    Act Density 0.035%

    No Known Activations