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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulates
    -0.07
    athing
    -0.06
    choices
    -0.06
    _query
    -0.06
    -standing
    -0.06
     sucht
    -0.06
    /pub
    -0.06
    -edge
    -0.06
     roses
    -0.06
    infos
    -0.06
    POSITIVE LOGITS
     حذ
    0.07
    .charAt
    0.07
     При
    0.07
    GetData
    0.07
     officers
    0.07
    .k
    0.07
    .documents
    0.07
     qx
    0.06
     quam
    0.06
    主任
    0.06
    Act Density 0.094%

    No Known Activations