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

    Neuronpedia

    INDEX
    Explanations

    reward points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tpl
    -0.06
    -data
    -0.06
     рецеп
    -0.06
     BOX
    -0.06
     tagName
    -0.06
     другими
    -0.06
    tığ
    -0.06
    .Geometry
    -0.06
     assets
    -0.06
     discounted
    -0.06
    POSITIVE LOGITS
     fright
    0.07
     حالی
    0.07
     інтер
    0.06
    _TERMIN
    0.06
     SENSOR
    0.06
     keeping
    0.06
     متف
    0.06
    EXIST
    0.06
     kadar
    0.06
     thảo
    0.06
    Act Density 0.004%

    No Known Activations