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

    Neuronpedia

    INDEX
    Explanations

    region

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Age
    -0.07
     measures
    -0.07
    tbl
    -0.07
     feared
    -0.07
    phas
    -0.07
    .onClick
    -0.07
    Simple
    -0.07
    劲
    -0.06
    סטוד
    -0.06
    .pen
    -0.06
    POSITIVE LOGITS
    _QU
    0.07
    _subscription
    0.07
    完毕
    0.07
     конкрет
    0.07
     happily
    0.07
    𐤓
    0.07
    .minecraft
    0.07
    .BLACK
    0.07
    ,long
    0.06
    <y
    0.06
    Act Density 0.006%

    No Known Activations