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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     annoyed
    -0.07
    files
    -0.07
    ственно
    -0.07
     अज
    -0.07
    bsites
    -0.07
     irresponsible
    -0.07
    ALA
    -0.07
     questi
    -0.06
     headquarters
    -0.06
    unk
    -0.06
    POSITIVE LOGITS
    _Application
    0.06
    stitution
    0.06
    );$
    0.06
    /Peak
    0.06
    .FileNotFoundException
    0.06
    -economic
    0.06
    issional
    0.06
     passphrase
    0.06
    )['
    0.06
    (itr
    0.06
    Act Density 0.083%

    No Known Activations