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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     دولتی
    -0.07
    CAPE
    -0.06
    PROP
    -0.06
     Amen
    -0.06
     muž
    -0.06
     compte
    -0.06
     जह
    -0.06
     disguised
    -0.06
    ออกแบบ
    -0.06
     mods
    -0.06
    POSITIVE LOGITS
    ünün
    0.07
    판
    0.06
    Principal
    0.06
    /message
    0.06
     Ellison
    0.06
    -du
    0.06
     Netherlands
    0.06
    -center
    0.06
    head
    0.06
     GENERATED
    0.06
    Act Density 0.023%

    No Known Activations