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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ndata
    -0.07
     strchr
    -0.06
     ""));↵
    -0.06
    extended
    -0.06
     fame
    -0.06
    た
    -0.06
     mereka
    -0.06
    )'↵
    -0.06
    Když
    -0.06
    ypsy
    -0.06
    POSITIVE LOGITS
    uctions
    0.07
    áln
    0.07
     photographed
    0.07
    arDown
    0.07
     repaint
    0.07
     toxic
    0.06
     intertwined
    0.06
    .Sign
    0.06
     More
    0.06
    ->↵
    0.06
    Act Density 0.008%

    No Known Activations