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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     στη
    -0.08
     testcase
    -0.06
    AU
    -0.06
     etiquette
    -0.06
     Triangle
    -0.06
    _mutex
    -0.06
     FINAL
    -0.06
     Receipt
    -0.06
    _address
    -0.06
     Metadata
    -0.06
    POSITIVE LOGITS
     sexuality
    0.07
    üny
    0.07
    ylül
    0.07
    нес
    0.07
    onedDateTime
    0.07
    wers
    0.06
     příspěv
    0.06
    ‌ال
    0.06
    ัดส
    0.06
    -forward
    0.06
    Act Density 0.014%

    No Known Activations