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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -)
    -0.07
    Median
    -0.07
     Reactive
    -0.07
    ificantly
    -0.07
    orous
    -0.07
    ernational
    -0.07
     fan
    -0.07
    Universal
    -0.07
    JC
    -0.06
     RD
    -0.06
    POSITIVE LOGITS
     vnode
    0.06
     spac
    0.06
    /socket
    0.06
    ULER
    0.06
    OMUX
    0.05
     Gdk
    0.05
     müş
    0.05
    singular
    0.05
     проп
    0.05
    Hello
    0.05
    Act Density 0.071%

    No Known Activations