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

    Neuronpedia

    INDEX
    Explanations

    code, URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <eos>
    -0.63
     &
    -0.46
    principalTable
    -0.46
    ']->
    -0.43
    ↵
    -0.42
    ~/
    -0.42
    /${
    -0.41
     U
    -0.41
    fr
    -0.41
     plus
    -0.40
    POSITIVE LOGITS
     مشين
    0.92
    expandindo
    0.85
     للمعارف
    0.84
     étrangère
    0.83
     ainfi
    0.82
    WriteBarrier
    0.75
     Theſe
    0.73
     fédé
    0.72
     Efq
    0.71
     Мексичка
    0.70
    Act Density 0.000%

    No Known Activations