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

    Neuronpedia

    INDEX
    Explanations

    steps before or after

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    üedad
    0.93
     enunciado
    0.91
     agrarian
    0.89
     Precinct
    0.88
    땔
    0.87
     dangerously
    0.85
     arma
    0.83
     deciduous
    0.83
     intramuscular
    0.82
     sash
    0.81
    POSITIVE LOGITS
    اد
    0.92
    at
    0.89
    أ
    0.88
    ر
    0.84
    心
    0.77
    و
    0.76
    ats
    0.76
    ه
    0.75
    <0xA0>
    0.75
    را
    0.72
    Act Density 0.001%

    No Known Activations