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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vation
    -0.07
     Tus
    -0.06
     nightclub
    -0.06
    lor
    -0.06
    _old
    -0.06
     RTVF
    -0.06
     rectangle
    -0.06
    	build
    -0.06
    Bird
    -0.06
     어떻게
    -0.06
    POSITIVE LOGITS
    <Service
    0.07
    ystack
    0.06
    (dot
    0.06
     superf
    0.06
     cinsel
    0.06
     постеп
    0.06
     �
    0.06
    Editar
    0.06
    иск
    0.06
    //
↵
↵
    0.06
    Act Density 0.012%

    No Known Activations