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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    broker
    -0.07
    .framework
    -0.07
    )this
    -0.06
    ')")↵
    -0.06
    ويت
    -0.06
    داشت
    -0.06
    anyak
    -0.06
    ену
    -0.06
    .setEmail
    -0.06
    _TO
    -0.06
    POSITIVE LOGITS
     ند
    0.06
     loser
    0.06
    (exc
    0.06
     acet
    0.06
    ('_
    0.06
    itored
    0.06
     indian
    0.06
    chant
    0.06
     flu
    0.06
     tetas
    0.06
    Act Density 0.091%

    No Known Activations