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

    Neuronpedia

    INDEX
    Explanations

    NAV

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ทาน
    -0.07
     zav
    -0.07
    ंच
    -0.07
    疫
    -0.07
     άν
    -0.07
     clean
    -0.07
     oggi
    -0.07
    iasco
    -0.06
    іб
    -0.06
    .prod
    -0.06
    POSITIVE LOGITS
    Terminate
    0.06
    목
    0.06
    	el
    0.06
    Gu
    0.06
     commissioned
    0.06
     mujeres
    0.06
    ographic
    0.06
     domin
    0.05
     XSS
    0.05
     круг
    0.05
    Act Density 0.004%

    No Known Activations