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

    Neuronpedia

    INDEX
    Explanations

    Romance languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     asserted
    -0.07
    勤
    -0.07
    .Obj
    -0.06
    (or
    -0.06
     Gods
    -0.06
    .hom
    -0.06
    	render
    -0.06
    plant
    -0.06
    "path
    -0.06
     interfaces
    -0.06
    POSITIVE LOGITS
    AGES
    0.07
     ⌒
    0.07
     매매
    0.07
    .estado
    0.06
    �다
    0.06
    .quick
    0.06
    ดร
    0.06
    YST
    0.06
    _HAL
    0.06
     decentralized
    0.06
    Act Density 0.013%

    No Known Activations