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

    Neuronpedia

    INDEX
    Explanations

    talk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _lim
    -0.08
    托
    -0.07
    ега
    -0.07
     challenges
    -0.07
    力
    -0.06
    -linear
    -0.06
     lb
    -0.06
     чор
    -0.06
    گران
    -0.06
    นค
    -0.06
    POSITIVE LOGITS
    发出
    0.07
    endDate
    0.06
     laptops
    0.06
    <decltype
    0.06
     Fixes
    0.06
    utf
    0.06
     laptop
    0.06
    <body
    0.06
     đại
    0.06
    _fs
    0.06
    Act Density 0.015%

    No Known Activations