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

    Neuronpedia

    INDEX
    Explanations

    ide suffix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dissolved
    -0.07
     monument
    -0.07
    int
    -0.06
     giữa
    -0.06
     lending
    -0.06
     disarm
    -0.06
    OUNTER
    -0.06
    κα
    -0.06
     setbacks
    -0.06
     teas
    -0.06
    POSITIVE LOGITS
    ('/:
    0.07
    ='".
    0.07
     downloader
    0.07
     Ballard
    0.07
    .environment
    0.07
    >>&
    0.06
    iệu
    0.06
    eşil
    0.06
     سریع
    0.06
    addin
    0.06
    Act Density 0.040%

    No Known Activations