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

    Neuronpedia

    INDEX
    Explanations

    time passing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    JECT
    -0.07
    ursions
    -0.06
    _preference
    -0.06
     합
    -0.06
    گیری
    -0.06
     institutes
    -0.05
    /_
    -0.05
    ,id
    -0.05
    polation
    -0.05
    faq
    -0.05
    POSITIVE LOGITS
     Handles
    0.07
    <Employee
    0.07
    {T
    0.07
    ，把
    0.06
     batching
    0.06
     wedding
    0.06
     seams
    0.06
     Conj
    0.06
     conventional
    0.06
     华
    0.06
    Act Density 0.021%

    No Known Activations