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

    Neuronpedia

    INDEX
    Explanations

    assistance and suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Canvas
    -0.07
    zt
    -0.06
    �
    -0.06
    |↵
    -0.06
     resembl
    -0.06
    胆
    -0.06
    Handles
    -0.06
    iframe
    -0.06
    .fragment
    -0.06
    Checked
    -0.06
    POSITIVE LOGITS
    鑑
    0.07
    (vp
    0.07
    οκ
    0.06
     Chuck
    0.06
    ~
    0.06
    %%%%
    0.06
     
    0.06
    _nm
    0.06
     όπου
    0.06
    esion
    0.06
    Act Density 0.086%

    No Known Activations