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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _quit
    -0.07
     Pete
    -0.06
     GetUser
    -0.06
    -chevron
    -0.06
    frame
    -0.06
    /student
    -0.06
     UPS
    -0.06
     Ahead
    -0.06
    �
    -0.06
    )=>{↵
    -0.06
    POSITIVE LOGITS
     resent
    0.07
     repell
    0.07
     advisors
    0.06
     driven
    0.06
    ertos
    0.06
    196
    0.06
    .m
    0.06
    Perform
    0.06
    нов
    0.06
     möglich
    0.06
    Act Density 0.015%

    No Known Activations