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
     Womens
    -0.07
     by
    -0.07
     OU
    -0.07
     лі
    -0.06
     xen
    -0.06
     فتح
    -0.06
     �
    -0.06
    æ
    -0.06
     �
    -0.06
    neys
    -0.06
    POSITIVE LOGITS
    朋
    0.07
    suggest
    0.07
     biçim
    0.06
     endlessly
    0.06
    .Raycast
    0.06
     т
    0.06
    .SwingConstants
    0.06
     Todos
    0.06
     ^{}
    0.06
     filesize
    0.06
    Act Density 0.019%

    No Known Activations