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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    췐
    -0.07
     Cub
    -0.06
     mệnh
    -0.06
    	dest
    -0.06
     demolished
    -0.06
    нд
    -0.06
     ~=
    -0.06
    (right
    -0.06
    inspect
    -0.06
    -powered
    -0.06
    POSITIVE LOGITS
    �
    0.07
    主持
    0.07
    pts
    0.07
    timer
    0.07
    �
    0.06
     thơ
    0.06
    .ham
    0.06
     prostitutes
    0.06
     exposing
    0.06
     bỏ
    0.06
    Act Density 0.005%

    No Known Activations