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
    (Build
    -0.06
     Saudi
    -0.06
    ่อไป
    -0.06
    _staff
    -0.06
     sweater
    -0.06
     relacion
    -0.06
    <Person
    -0.06
    iesz
    -0.06
    .STATE
    -0.06
    def
    -0.06
    POSITIVE LOGITS
    еств
    0.07
    .unsubscribe
    0.07
    노
    0.06
    ambre
    0.06
     jednotlivých
    0.06
    ستی
    0.06
     різних
    0.06
     spectro
    0.06
     odmít
    0.06
    texts
    0.06
    Act Density 0.025%

    No Known Activations