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

    Neuronpedia

    INDEX
    Explanations

    cavities in technical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /fast
    -0.06
     chú
    -0.06
    EqualTo
    -0.06
     stem
    -0.06
    contro
    -0.06
     sourced
    -0.06
    ))),
    -0.06
     ↵	↵
    -0.06
    cd
    -0.06
    tems
    -0.06
    POSITIVE LOGITS
     MIME
    0.07
     наших
    0.07
    YE
    0.07
    PAY
    0.06
     ara
    0.06
    _business
    0.06
     Pink
    0.06
    ’ai
    0.06
     fines
    0.06
    빈
    0.06
    Act Density 0.024%

    No Known Activations