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

    Neuronpedia

    INDEX
    Explanations

    racing interviews/ reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     based
    -0.07
    Fan
    -0.07
     siege
    -0.06
     sail
    -0.06
    udur
    -0.06
     когда
    -0.06
     malfunction
    -0.06
     će
    -0.06
    addons
    -0.06
    inance
    -0.06
    POSITIVE LOGITS
    їв
    0.07
    ินค
    0.07
    异常
    0.06
    ---↵
    0.06
    ิด
    0.06
    фик
    0.06
     пля
    0.06
     aqu
    0.06
     ##
    0.06
    0.06
    Act Density 0.006%

    No Known Activations