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

    Neuronpedia

    INDEX
    Explanations

    propagation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     downfall
    -0.07
     发
    -0.07
     Shades
    -0.07
     Trout
    -0.07
     AIR
    -0.07
    SUPER
    -0.06
     Devils
    -0.06
    CREASE
    -0.06
     dye
    -0.06
    驗
    -0.06
    POSITIVE LOGITS
    (Socket
    0.07
    Robert
    0.06
    短暂
    0.06
    뒀
    0.06
    ⓛ
    0.06
    vector
    0.06
    maktadır
    0.06
     côt
    0.06
    bairro
    0.06
    녁
    0.06
    Act Density 0.002%

    No Known Activations