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
    329
    -0.06
     rồi
    -0.06
     　　　　　　　
    -0.06
     trunk
    -0.06
    、彼
    -0.06
    -0.05
    .NotFound
    -0.05
    лов
    -0.05
    ีข
    -0.05
     eventdata
    -0.05
    POSITIVE LOGITS
    (火
    0.07
    kul
    0.07
     sach
    0.07
    _rep
    0.07
    omed
    0.07
    احل
    0.06
    ToRemove
    0.06
     unicode
    0.06
    asis
    0.06
     Base
    0.06
    Act Density 0.005%

    No Known Activations