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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Person
    -0.06
     deepen
    -0.06
    _aw
    -0.06
     直
    -0.06
    .Slf
    -0.06
    цев
    -0.06
    timezone
    -0.06
    .Parcelable
    -0.06
     exacerbated
    -0.06
    Longitude
    -0.06
    POSITIVE LOGITS
     ασ
    0.07
    .pattern
    0.07
    军
    0.07
    Controller
    0.06
     Anything
    0.06
     laptops
    0.06
    105
    0.06
    συ
    0.06
    .ali
    0.06
    σμο
    0.06
    Act Density 0.001%

    No Known Activations