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

    Neuronpedia

    INDEX
    Explanations

    showing someone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mug
    -0.07
    _impl
    -0.07
     versions
    -0.06
     sembl
    -0.06
    lei
    -0.06
    рещ
    -0.06
     fiscal
    -0.06
     march
    -0.06
    Tab
    -0.06
    Labour
    -0.06
    POSITIVE LOGITS
    trag
    0.06
    CLUSION
    0.06
    .prop
    0.06
     vex
    0.06
     ngại
    0.06
    rogen
    0.06
     notified
    0.06
    expo
    0.06
     verdade
    0.06
     recebe
    0.06
    Act Density 0.011%

    No Known Activations