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

    Neuronpedia

    INDEX
    Explanations

    Formal/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Td
    -0.07
     다
    -0.06
     everyone
    -0.06
     xa
    -0.06
    KG
    -0.06
     ja
    -0.06
     откры
    -0.06
     plaintiff
    -0.06
     Economist
    -0.06
    ocê
    -0.06
    POSITIVE LOGITS
     Aires
    0.07
    gpio
    0.06
    िजन
    0.06
    adic
    0.06
    hire
    0.06
    ør
    0.06
     prés
    0.06
     쇼
    0.06
    ังกล
    0.06
     targ
    0.06
    Act Density 0.682%

    No Known Activations