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

    Neuronpedia

    INDEX
    Explanations

    appeared

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AE
    -0.07
     minds
    -0.07
    ']↵
    -0.06
    HEMA
    -0.06
    .help
    -0.06
    设备
    -0.06
     Midlands
    -0.06
    Data
    -0.06
    Monkey
    -0.06
    .getWorld
    -0.06
    POSITIVE LOGITS
     SolidColorBrush
    0.07
     спів
    0.06
    iking
    0.06
    onto
    0.06
    played
    0.06
    .skill
    0.06
     }}</
    0.06
    Util
    0.06
    ransition
    0.06
     ◆
    0.06
    Act Density 0.015%

    No Known Activations