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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rio
    -0.07
     всем
    -0.06
    oufl
    -0.06
     warmly
    -0.06
    _JOIN
    -0.06
     blanket
    -0.06
     roam
    -0.06
    sut
    -0.06
     Discount
    -0.06
    xAC
    -0.06
    POSITIVE LOGITS
     
    0.07
     councils
    0.07
     дозволя
    0.07
     li
    0.06
     Produkte
    0.06
    +l
    0.06
     k
    0.06
     Ov
    0.06
    으나
    0.06
    -ev
    0.06
    Act Density 0.000%

    No Known Activations