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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -,
    -0.07
    _blueprint
    -0.07
    Bindable
    -0.06
     ever
    -0.06
     transporter
    -0.06
    .Window
    -0.06
     attendee
    -0.06
     ls
    -0.06
    -sponsored
    -0.06
     scrolling
    -0.06
    POSITIVE LOGITS
    write
    0.07
     Vir
    0.07
    Vir
    0.07
     exem
    0.07
    니다
    0.07
    šit
    0.06
     erg
    0.06
    PPER
    0.06
    icient
    0.06
    ул
    0.06
    Act Density 0.032%

    No Known Activations