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

    Neuronpedia

    INDEX
    Explanations

    listing items or including

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $total
    -0.07
     THB
    -0.06
     caf
    -0.06
    Р
    -0.06
     yol
    -0.06
     suk
    -0.06
    Phones
    -0.06
    Non
    -0.06
     incididunt
    -0.06
    яч
    -0.06
    POSITIVE LOGITS
     XPath
    0.07
    oling
    0.07
     stdClass
    0.06
    .dictionary
    0.06
     проп
    0.06
     cleanly
    0.06
    therapy
    0.06
    oupper
    0.06
     homelessness
    0.06
    .removeAttribute
    0.06
    Act Density 0.027%

    No Known Activations