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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pořad
    -0.07
     persec
    -0.07
     Vad
    -0.06
     icing
    -0.06
     RUNNING
    -0.06
     над
    -0.06
    }")
↵
    -0.06
    大人
    -0.06
    routes
    -0.06
     declared
    -0.06
    POSITIVE LOGITS
    placer
    0.06
    　　　 　 　 　
    0.06
     постеп
    0.06
    <Self
    0.06
    Sac
    0.06
     pouco
    0.06
    IOD
    0.06
     bylo
    0.06
    ãn
    0.05
     legislation
    0.05
    Act Density 0.067%

    No Known Activations