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

    Neuronpedia

    INDEX
    Explanations

    dialogues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ό
    -0.07
     таком
    -0.07
    ný
    -0.06
    нах
    -0.06
     女
    -0.06
     unab
    -0.06
     开
    -0.06
     редак
    -0.06
    ница
    -0.06
    ящ
    -0.06
    POSITIVE LOGITS
     sûr
    0.07
     laptops
    0.07
     agregar
    0.06
    _tbl
    0.06
     Charger
    0.06
     affordable
    0.06
    actoring
    0.06
    intern
    0.06
     wifi
    0.06
     textAlign
    0.06
    Act Density 0.015%

    No Known Activations