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
     Large
    -0.07
     McC
    -0.07
    원을
    -0.06
     hoog
    -0.06
    imei
    -0.06
    -star
    -0.06
     Dee
    -0.06
    Reference
    -0.06
    -overlay
    -0.06
    eneg
    -0.06
    POSITIVE LOGITS
     přiz
    0.07
     unsett
    0.07
    plays
    0.06
     operate
    0.06
    replace
    0.06
    Invoker
    0.06
     khiển
    0.06
     înt
    0.06
     खतर
    0.06
    chemy
    0.06
    Act Density 0.001%

    No Known Activations