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

    Neuronpedia

    INDEX
    Explanations

    100

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trudeau
    -0.07
    .Function
    -0.06
     OPTIONAL
    -0.06
    510
    -0.06
    nst
    -0.06
     ambush
    -0.06
     Э
    -0.06
    .getCode
    -0.06
     Guru
    -0.06
    -bg
    -0.06
    POSITIVE LOGITS
    Sort
    0.07
     آمده
    0.07
    orta
    0.07
     Searching
    0.07
    unned
    0.07
    ,$
    0.06
     Jennifer
    0.06
    歌
    0.06
    Assistant
    0.06
     serde
    0.06
    Act Density 4.665%

    No Known Activations