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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    евой
    -0.07
    时时
    -0.07
    名为
    -0.06
     İşte
    -0.06
     I
    -0.06
    官员
    -0.06
     Gon
    -0.06
    勇敢
    -0.06
    即时
    -0.06
    setMessage
    -0.06
    POSITIVE LOGITS
     Mot
    0.07
    mgr
    0.07
    hub
    0.07
    Distinct
    0.07
    &q
    0.06
    �
    0.06
     unfold
    0.06
    _leaf
    0.06
    썸
    0.06
    โลก
    0.06
    Act Density 0.006%

    No Known Activations