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

    Neuronpedia

    INDEX
    Explanations

    tracking and labeling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Тем
    -0.07
     strands
    -0.06
    Fully
    -0.06
     Cummings
    -0.06
    (hand
    -0.06
    ighet
    -0.06
     siege
    -0.06
     mening
    -0.06
    隠
    -0.06
     what
    -0.06
    POSITIVE LOGITS
     mö
    0.07
    _lua
    0.07
     рамках
    0.07
    ="">
↵
    0.07
    џџџџ
    0.06
    "){
↵
    0.06
    _FATAL
    0.06
    ≥
    0.06
     списка
    0.06
    WithData
    0.06
    Act Density 0.249%

    No Known Activations