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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    獍
    -0.07
     تقدي
    -0.07
    悃
    -0.07
     cheerful
    -0.07
    整齐
    -0.07
    全日
    -0.07
    Bell
    -0.07
     Governments
    -0.07
    leftright
    -0.07
    setDescription
    -0.07
    POSITIVE LOGITS
     ops
    0.07
    잇
    0.07
     Brady
    0.07
    密码
    0.07
     실행
    0.07
    	HANDLE
    0.06
    繁殖
    0.06
    iar
    0.06
     celebrity
    0.06
     queda
    0.06
    Act Density 0.001%

    No Known Activations