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

    Neuronpedia

    INDEX
    Explanations

    ology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OA
    -0.07
     koji
    -0.06
     melan
    -0.06
     tedbir
    -0.06
    وله
    -0.06
    ाएग
    -0.06
    spot
    -0.06
    .jpa
    -0.06
     Meditation
    -0.06
     бед
    -0.06
    POSITIVE LOGITS
     Global
    0.07
    onestly
    0.07
     scams
    0.07
    Grace
    0.06
     economically
    0.06
    Checked
    0.06
    ('__
    0.06
    defined
    0.06
     *
↵
    0.06
     meticulously
    0.06
    Act Density 0.001%

    No Known Activations