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

    Neuronpedia

    INDEX
    Explanations

    uter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    –and
    -0.07
    /of
    -0.07
     云
    -0.07
    .enums
    -0.06
    lus
    -0.06
    -tw
    -0.06
     applicants
    -0.06
    asions
    -0.06
     人
    -0.06
    liž
    -0.06
    POSITIVE LOGITS
     draw
    0.07
     Schumer
    0.06
     helium
    0.06
    ρκεια
    0.06
     DEA
    0.06
     Thur
    0.06
    _DGRAM
    0.06
     Heidi
    0.06
    auer
    0.06
    (_("
    0.06
    Act Density 0.001%

    No Known Activations