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

    Neuronpedia

    INDEX
    Explanations

    connecting devices/networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compounds
    -0.07
    vůli
    -0.07
     önce
    -0.07
     Eine
    -0.07
     zosta
    -0.06
    Mil
    -0.06
     Hus
    -0.06
    .elem
    -0.06
    하려
    -0.06
    úde
    -0.06
    POSITIVE LOGITS
    "label
    0.07
    inium
    0.07
    ¨¨
    0.06
    /git
    0.06
     今
    0.06
    .percent
    0.06
    (sockfd
    0.06
     Recording
    0.06
     суд
    0.06
     cosmos
    0.06
    Act Density 0.037%

    No Known Activations