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

    Neuronpedia

    INDEX
    Explanations

    Made of, parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nurs
    -0.07
    ального
    -0.07
     prosince
    -0.07
     shed
    -0.06
    .signIn
    -0.06
     Patch
    -0.06
     facets
    -0.06
    �
    -0.06
     kuzey
    -0.06
    Inter
    -0.06
    POSITIVE LOGITS
    zyć
    0.07
    double
    0.07
     searchBar
    0.06
     모델
    0.06
    =name
    0.06
     responsable
    0.06
    resident
    0.06
    sanitize
    0.06
     clearColor
    0.06
    ISTORY
    0.05
    Act Density 0.071%

    No Known Activations