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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cars
    -0.07
    iky
    -0.07
    	Http
    -0.07
     Arts
    -0.06
    Compute
    -0.06
     ilişkin
    -0.06
     Mansion
    -0.06
     Ment
    -0.06
    .getColumn
    -0.06
    .Co
    -0.06
    POSITIVE LOGITS
    -dem
    0.06
     gramm
    0.06
    names
    0.06
    レビ
    0.06
    =_
    0.06
    感じ
    0.06
     tok
    0.06
    ${
    0.06
    removeClass
    0.06
    .'<
    0.06
    Act Density 0.001%

    No Known Activations