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

    Neuronpedia

    INDEX
    Explanations

    code/data delimited by symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ACCOUNT
    -0.07
     Python
    -0.07
    XObject
    -0.07
    /qt
    -0.07
    rangle
    -0.06
     python
    -0.06
     و
    -0.06
     climb
    -0.06
    .Template
    -0.06
     上
    -0.06
    POSITIVE LOGITS
    ạy
    0.06
    争
    0.06
    -Cds
    0.06
    forder
    0.06
    -names
    0.06
     Marshall
    0.06
    -focus
    0.06
    鸡
    0.06
     нарез
    0.05
     dead
    0.05
    Act Density 0.016%

    No Known Activations