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

    Neuronpedia

    INDEX
    Explanations

    Procedure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    661
    -0.06
     菲律宾申博
    -0.06
    (name
    -0.06
    [token
    -0.06
    /m
    -0.06
    663
    -0.06
    /G
    -0.06
    (Page
    -0.06
    فته
    -0.06
    /f
    -0.06
    POSITIVE LOGITS
     Juice
    0.07
    ้ผ
    0.06
    命周期
    0.06
     cdecl
    0.06
    ister
    0.06
     SUCH
    0.06
     ultimo
    0.06
    ightly
    0.06
     sâu
    0.06
     thẳng
    0.06
    Act Density 0.001%

    No Known Activations