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

    Neuronpedia

    INDEX
    Explanations

    [@

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _endpoint
    -0.07
     pulmonary
    -0.07
     iris
    -0.07
     afl
    -0.07
     legalization
    -0.06
     Thy
    -0.06
    ,var
    -0.06
     双
    -0.06
     Ran
    -0.06
    -guard
    -0.06
    POSITIVE LOGITS
    чний
    0.07
    .Marker
    0.06
    操作
    0.06
    _refl
    0.06
     verschiedenen
    0.06
    utan
    0.06
    filtro
    0.06
     born
    0.06
    .fm
    0.06
     ¬
    0.06
    Act Density 0.041%

    No Known Activations