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

    Neuronpedia

    INDEX
    Explanations

    protected

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Else
    -0.07
    xcb
    -0.07
    쇄
    -0.07
    .Cho
    -0.06
    öt
    -0.06
    ủ
    -0.06
    iven
    -0.06
    �
    -0.06
    edm
    -0.06
     AVG
    -0.06
    POSITIVE LOGITS
    ："
    0.07
    %↵
    0.07
    :"↵
    0.07
     '%'
    0.07
    מוני
    0.07
    >;↵
    0.07
    🐩
    0.07
    Detach
    0.07
    矫正
    0.06
    Ք
    0.06
    Act Density 0.001%

    No Known Activations