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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     מוכר
    -0.08
     önem
    -0.08
    靬
    -0.07
    _ENSURE
    -0.07
    abad
    -0.07
    way
    -0.07
     Zug
    -0.07
    :href
    -0.06
    ’ét
    -0.06
     أكد
    -0.06
    POSITIVE LOGITS
     Feather
    0.07
    Practice
    0.07
     Creat
    0.07
    .multi
    0.07
     Metric
    0.07
     retros
    0.07
    Deleted
    0.07
     rins
    0.07
     Receive
    0.07
     empirical
    0.07
    Act Density 0.018%

    No Known Activations