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
     Philly
    -0.06
     лиц
    -0.06
     Industrial
    -0.06
     düşük
    -0.06
     cared
    -0.06
     caliente
    -0.06
    .ind
    -0.06
     Likewise
    -0.06
     detta
    -0.06
    (NAME
    -0.06
    POSITIVE LOGITS
    corlib
    0.08
    .viewer
    0.07
    責
    0.07
    DTV
    0.06
     Gallery
    0.06
    XMLLoader
    0.06
     defeated
    0.06
    .embedding
    0.06
    ยนตร
    0.06
     neob
    0.06
    Act Density 0.003%

    No Known Activations