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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     freeway
    -0.08
     Chil
    -0.08
    :https
    -0.07
    仕事
    -0.07
    är
    -0.07
     Sol
    -0.07
     inflam
    -0.07
     male
    -0.07
     dictates
    -0.07
    created
    -0.07
    POSITIVE LOGITS
     JFile
    0.09
     ಮಾಡಲು
    0.09
     查看
    0.09
     наж
    0.09
     asistencia
    0.08
     comando
    0.08
     thao
    0.08
     جاري
    0.08
     deseas
    0.08
     COMMAND
    0.08
    Act Density 0.015%

    No Known Activations