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

    Neuronpedia

    INDEX
    Explanations

    Code/tests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nombre
    -0.07
    七
    -0.06
     Dirt
    -0.06
     assistance
    -0.06
     dir
    -0.06
    Besides
    -0.06
     discrepancy
    -0.06
     heroes
    -0.06
    ์กร
    -0.06
    science
    -0.06
    POSITIVE LOGITS
    _portfolio
    0.07
     повер
    0.07
     κατά
    0.07
    арам
    0.06
    mekte
    0.06
     lstm
    0.06
    ่องเท
    0.06
     posledních
    0.06
    contres
    0.06
     Calcium
    0.06
    Act Density 0.022%

    No Known Activations