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

    Neuronpedia

    INDEX
    Explanations

    math problems with numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pr
    -0.08
    "),
    -0.08
     UI
    -0.07
    '),
    -0.07
     dispoz
    -0.07
    ifi
    -0.07
    #[
    -0.07
    time
    -0.06
    .time
    -0.06
    ノ
    -0.06
    POSITIVE LOGITS
     каш
    0.09
     زیات
    0.09
     უთ
    0.09
     बढी
    0.09
    ​ព
    0.09
     кет
    0.09
     һөйл
    0.09
    იერთ
    0.09
     თანამშრომ
    0.09
     компенса
    0.09
    Act Density 0.048%

    No Known Activations