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

    Neuronpedia

    INDEX
    Explanations

    "Founded in" dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prm
    -0.08
     불
    -0.07
    imary
    -0.07
     comprises
    -0.07
    _geom
    -0.07
    bom
    -0.07
    妙
    -0.07
     selv
    -0.07
    _parameter
    -0.07
    _props
    -0.07
    POSITIVE LOGITS
    以来
    0.12
     edən
    0.09
     sejak
    0.09
    ​ការ
    0.08
    年以来
    0.08
    ，总
    0.08
     কৰিছে
    0.08
     અત્યાર
    0.08
     কৰিছিল
    0.08
     davam
    0.08
    Act Density 0.063%

    No Known Activations