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

    Neuronpedia

    INDEX
    Explanations

    stock or game

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Flexible
    0.96
    模块
    0.92
    RG
    0.91
     módulo
    0.90
    screenshot
    0.88
    Relative
    0.87
    Experienced
    0.86
    ྕ
    0.85
     eyeb
    0.85
     provoke
    0.84
    POSITIVE LOGITS
    ू
    0.78
    ي
    0.76
    asını
    0.73
     becoming
    0.69
    ঘরের
    0.67
    ori
    0.66
    ัน
    0.66
    istico
    0.65
    зи
    0.65
    utu
    0.65
    Act Density 0.261%

    No Known Activations