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

    Neuronpedia

    INDEX
    Explanations

    zy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Verification
    -0.07
    /notification
    -0.07
     interstate
    -0.07
     trafficking
    -0.07
     explain
    -0.06
    рек
    -0.06
     dů
    -0.06
     Shipping
    -0.06
    direccion
    -0.06
     ”↵↵
    -0.06
    POSITIVE LOGITS
    _HERE
    0.06
     blob
    0.06
     kích
    0.06
     cây
    0.06
    RowAnimation
    0.06
     مخت
    0.06
    plements
    0.06
     �
    0.06
     Massachusetts
    0.06
    GLfloat
    0.06
    Act Density 0.089%

    No Known Activations