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

    Neuronpedia

    INDEX
    Explanations

    ep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -
↵
    -0.06
     Stamford
    -0.06
     Samantha
    -0.06
    讓
    -0.06
    Transform
    -0.06
     cult
    -0.06
    editor
    -0.06
    wy
    -0.06
    รด
    -0.06
    -span
    -0.06
    POSITIVE LOGITS
    ":
    0.07
    итор
    0.06
    ToDate
    0.06
     المك
    0.06
     vat
    0.06
    .moveToFirst
    0.06
    tah
    0.06
    ctp
    0.06
    439
    0.06
     RemoteException
    0.06
    Act Density 0.000%

    No Known Activations