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

    Neuronpedia

    INDEX
    Explanations

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     چرا
    -0.07
     nc
    -0.06
    -0.06
    (ti
    -0.06
    Thirty
    -0.06
     twenty
    -0.06
    очь
    -0.06
     leicht
    -0.06
     puesto
    -0.06
     quoi
    -0.06
    POSITIVE LOGITS
    영
    0.07
     Gupta
    0.07
    quartered
    0.06
    msg
    0.06
     warp
    0.06
     Gür
    0.06
     Contacts
    0.06
     graduate
    0.06
    _btn
    0.06
    ippers
    0.06
    Act Density 0.003%

    No Known Activations