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

    Neuronpedia

    INDEX
    Explanations

    export

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DETECT
    -0.07
     Hình
    -0.07
    oned
    -0.07
     мере
    -0.06
    _capacity
    -0.06
     方
    -0.06
    .Live
    -0.06
    병
    -0.06
    .neighbors
    -0.06
     CrossAxisAlignment
    -0.06
    POSITIVE LOGITS
     overly
    0.07
     missing
    0.06
    (public
    0.06
    EY
    0.06
     Eddie
    0.06
     Generates
    0.06
    /';↵↵
    0.06
    IAM
    0.06
    tp
    0.06
     oblivious
    0.06
    Act Density 0.001%

    No Known Activations