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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ackBar
    -0.07
    ادي
    -0.06
     broadcast
    -0.06
    ати
    -0.06
    CHK
    -0.06
     agree
    -0.06
     ves
    -0.06
    igators
    -0.06
    宿
    -0.05
    _share
    -0.05
    POSITIVE LOGITS
    .pretty
    0.07
    ，现在
    0.07
     Christianity
    0.07
    !("{
    0.07
    <a
    0.07
     dout
    0.07
    "F
    0.06
     пок
    0.06
    ”,
    0.06
    "',↵
    0.06
    Act Density 0.064%

    No Known Activations