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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     my
    -0.08
    ящих
    -0.07
     نوع
    -0.06
     Dates
    -0.06
    ไข
    -0.06
    flt
    -0.06
     accounts
    -0.06
    folk
    -0.06
    alez
    -0.06
     meinen
    -0.06
    POSITIVE LOGITS
    лор
    0.07
    ...]
    0.07
     fulfillment
    0.07
     han
    0.07
    @implementation
    0.06
     WOM
    0.06
    吧
    0.06
    'yi
    0.06
     retorn
    0.06
    "github
    0.06
    Act Density 0.353%

    No Known Activations