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

    Neuronpedia

    INDEX
    Explanations

    books and writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Registration
    -0.09
     Instructor
    -0.09
     Manuals
    -0.08
     JAXBElement
    -0.08
     Trainings
    -0.08
     Pago
    -0.08
    UMIN
    -0.08
     Trainer
    -0.08
     Puntland
    -0.08
     Pvt
    -0.08
    POSITIVE LOGITS
     argues
    0.10
     anecdotes
    0.09
     arguing
    0.09
     essay
    0.09
     essays
    0.09
     arguments
    0.09
     argue
    0.09
     empathy
    0.09
     argument
    0.09
     bestselling
    0.08
    Act Density 0.071%

    No Known Activations