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

    Neuronpedia

    INDEX
    Explanations

    STEM subjects

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CS
    2.21
    CS
    1.97
     cs
    1.93
     Computer
    1.87
    Computer
    1.82
     computer
    1.81
    cs
    1.79
    computer
    1.63
     컴퓨터
    1.59
     CSE
    1.52
    POSITIVE LOGITS
     वर्
    0.80
     Diageo
    0.71
    ಜ
    0.69
     পরিষদের
    0.69
     Tua
    0.68
     Tirol
    0.67
     chiedere
    0.67
     bricks
    0.66
     हिटलर
    0.65
     кирпи
    0.64
    Act Density 0.079%

    No Known Activations