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

    Neuronpedia

    INDEX
    Explanations

    spread

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beasts
    -0.08
     gravida
    -0.08
     резерв
    -0.08
     taxpayers
    -0.07
     Taurus
    -0.07
    wür
    -0.07
     mangan
    -0.07
     తయ
    -0.07
    ania
    -0.07
    gänge
    -0.07
    POSITIVE LOGITS
    传播
    0.14
     फैल
    0.13
     dissemination
    0.12
     rộng
    0.11
     spreading
    0.11
     dissemin
    0.11
     ಹರ
    0.11
     verspre
    0.10
     misinformation
    0.10
     распространя
    0.10
    Act Density 0.042%

    No Known Activations