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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ister
    -0.07
     Voor
    -0.07
    μ
    -0.07
     pension
    -0.07
    istics
    -0.06
     temptation
    -0.06
    。（
    -0.06
    潽
    -0.06
    姓
    -0.06
     שני
    -0.06
    POSITIVE LOGITS
    foobar
    0.08
     //"
    0.07
     /^[
    0.07
    _found
    0.07
    ////////////////
    0.07
     }}">
    0.07
     знач
    0.07
    THREAD
    0.07
    >Hello
    0.07
    trash
    0.06
    Act Density 0.001%

    No Known Activations