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

    Neuronpedia

    INDEX
    Explanations

    adding new elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gravy
    -0.07
     مجلس
    -0.06
    ỗng
    -0.06
    κτή
    -0.06
    _Delay
    -0.06
    -reference
    -0.06
     wars
    -0.06
     weekends
    -0.06
     Reject
    -0.06
     grocery
    -0.06
    POSITIVE LOGITS
    .onClick
    0.07
    Ι
    0.07
     yearly
    0.07
     magazines
    0.07
     Pam
    0.06
    ひと
    0.06
    |$
    0.06
    기의
    0.06
    па
    0.06
    HEST
    0.06
    Act Density 0.018%

    No Known Activations