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

    Neuronpedia

    INDEX
    Explanations

    code and databases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     полож
    -0.06
    ITTLE
    -0.06
    70
    -0.06
    Dismiss
    -0.06
    limited
    -0.06
    keys
    -0.06
    gomery
    -0.06
    UV
    -0.06
     CDs
    -0.06
     sings
    -0.06
    POSITIVE LOGITS
     людей
    0.07
     用户
    0.07
    _DST
    0.06
     οπο
    0.06
     adap
    0.06
     серд
    0.06
     cunning
    0.06
     المخت
    0.06
    apus
    0.06
    ::*
    0.06
    Act Density 0.012%

    No Known Activations