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

    Neuronpedia

    INDEX
    Explanations

    as in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ست
    -0.08
    ادات
    -0.06
     Frances
    -0.06
     ilişk
    -0.06
    샤
    -0.06
     přech
    -0.06
    .card
    -0.06
     læ
    -0.06
     Commons
    -0.06
     commons
    -0.06
    POSITIVE LOGITS
    ?>↵
    0.07
    许
    0.06
     |_
    0.06
    	callback
    0.06
    参与
    0.06
     pers
    0.06
     nig
    0.06
    buch
    0.06
    不好
    0.06
     yahoo
    0.06
    Act Density 0.020%

    No Known Activations