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

    Neuronpedia

    INDEX
    Explanations

    US presidents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chemist
    -0.07
     Destructor
    -0.07
    (schedule
    -0.06
    way
    -0.06
    گیرد
    -0.06
    Forge
    -0.06
     Simone
    -0.06
    ';";↵
    -0.06
     pipes
    -0.06
     Porsche
    -0.06
    POSITIVE LOGITS
    *\
    0.07
    =w
    0.07
    [n
    0.06
    [f
    0.06
    .postValue
    0.06
    absolute
    0.06
    ผล
    0.06
     изображ
    0.06
    另一
    0.06
    $,
    0.06
    Act Density 0.016%

    No Known Activations