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
    酉
    -0.07
     certifications
    -0.07
    充满
    -0.07
    融入
    -0.07
    事业发展
    -0.07
     Colleges
    -0.06
     road
    -0.06
    ᠩ
    -0.06
    .DataAccess
    -0.06
    辏
    -0.06
    POSITIVE LOGITS
    ивать
    0.07
     jp
    0.07
     vídeo
    0.07
     то
    0.07
     discard
    0.07
     whole
    0.07
     רוצים
    0.06
    .textField
    0.06
    	angle
    0.06
    -spec
    0.06
    Act Density 0.001%

    No Known Activations