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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BUG
    -0.08
     Gim
    -0.07
    _dis
    -0.07
    _Project
    -0.07
    -move
    -0.07
     campground
    -0.07
    .notice
    -0.07
    场馆
    -0.07
    .Connect
    -0.07
    实现了
    -0.06
    POSITIVE LOGITS
    などが
    0.07
     Angola
    0.07
    isArray
    0.07
     SERVICES
    0.07
    oralType
    0.07
    んじゃないか
    0.07
    _builder
    0.07
    比特
    0.07
    uffled
    0.07
     architecture
    0.07
    Act Density 0.014%

    No Known Activations