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

    Neuronpedia

    INDEX
    Explanations

    file paths and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ols
    0.72
    ပိုင်း
    0.64
     বিতরণ
    0.64
     enfe
    0.63
     শুভে
    0.62
    ere
    0.61
     Allies
    0.61
    𝗁
    0.61
     Democrats
    0.60
    ાસ
    0.60
    POSITIVE LOGITS
    4
    1.01
    8
    0.91
    7
    0.83
    是
    0.82
    3
    0.79
    6
    0.79
    ۔
    0.71
    1
    0.65
    は
    0.65
    는
    0.64
    Act Density 0.000%

    No Known Activations