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

    Neuronpedia

    INDEX
    Explanations

    Reaching a goal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eas
    -0.06
     Vegetable
    -0.06
    .ToShort
    -0.06
    玲
    -0.06
     réal
    -0.06
    `;↵↵
    -0.05
    “,
    -0.05
     Mild
    -0.05
    ド
    -0.05
    ými
    -0.05
    POSITIVE LOGITS
     был
    0.07
    ặc
    0.06
    .BLUE
    0.06
     služ
    0.06
    navbar
    0.06
    バー
    0.06
     funky
    0.06
    ถาน
    0.06
     proponents
    0.06
    “(
    0.06
    Act Density 0.042%

    No Known Activations