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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .qu
    -0.07
     CheckBox
    -0.07
    _TRACE
    -0.07
    stm
    -0.07
     Archive
    -0.07
    한
    -0.07
    .mouse
    -0.07
    _TOOL
    -0.07
     itemType
    -0.07
    藝
    -0.06
    POSITIVE LOGITS
     Examples
    0.07
    औ
    0.06
    nts
    0.06
     Wand
    0.06
    就连
    0.06
    yaw
    0.06
    olah
    0.06
    砸
    0.06
    志愿
    0.06
    -----------
↵
    0.06
    Act Density 0.003%

    No Known Activations