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

    Neuronpedia

    INDEX
    Explanations

    dates, times, questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dazz
    -0.07
     dataArray
    -0.07
     leave
    -0.07
     cruiser
    -0.07
     Hut
    -0.07
     murderous
    -0.07
     taxis
    -0.07
    icle
    -0.07
     Magnet
    -0.07
    -inspired
    -0.06
    POSITIVE LOGITS
    .jackson
    0.07
    924
    0.06
    .AspNetCore
    0.06
    dub
    0.06
    getDescription
    0.06
    ив
    0.06
     assigned
    0.06
    赫
    0.05
    ьому
    0.05
    //↵↵↵
    0.05
    Act Density 0.001%

    No Known Activations