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

    Neuronpedia

    INDEX
    Explanations

    file paths and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gamma
    -0.07
     addict
    -0.07
    chl
    -0.06
     tent
    -0.06
     boolean
    -0.06
     P
    -0.06
     L
    -0.06
    ologist
    -0.06
    Architecture
    -0.06
    협
    -0.06
    POSITIVE LOGITS
    ليزية
    0.06
    頃
    0.06
     Wick
    0.06
    .tc
    0.06
    elif
    0.06
    鉄
    0.06
    .unregister
    0.06
    иной
    0.05
     položky
    0.05
    alice
    0.05
    Act Density 0.020%

    No Known Activations