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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    omething
    -0.06
    $n
    -0.06
     Frances
    -0.06
    leases
    -0.06
     допом
    -0.06
     Herbal
    -0.06
    've
    -0.06
    ním
    -0.06
     heures
    -0.06
     Gray
    -0.06
    POSITIVE LOGITS
     joked
    0.07
     maxx
    0.07
    ATYPE
    0.07
    mey
    0.06
     TResult
    0.06
     KEY
    0.06
    _expr
    0.06
     ViewBag
    0.06
    .dsl
    0.06
    //(
    0.06
    Act Density 0.019%

    No Known Activations