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

    Neuronpedia

    INDEX
    Explanations

    interface, machine, admin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.52
    at
    0.48
     React
    0.47
     New
    0.46
     Tues
    0.46
    ello
    0.45
    asm
    0.45
    ıma
    0.45
    i
    0.45
    ton
    0.44
    POSITIVE LOGITS
     criminals
    0.54
    وا
    0.52
    দা
    0.52
    ني
    0.50
    করিয়
    0.49
    را
    0.49
     игроков
    0.48
    ックス
    0.46
     coste
    0.46
    ن
    0.46
    Act Density 0.000%

    No Known Activations