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

    Neuronpedia

    INDEX
    Explanations

    abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    
    -0.07
     Soros
    -0.06
    Everyone
    -0.06
    券
    -0.06
     Williamson
    -0.06
    w
    -0.06
    다고
    -0.06
     tram
    -0.06
    jsx
    -0.06
    Accessor
    -0.06
    POSITIVE LOGITS
     beep
    0.07
     وت
    0.06
     Bark
    0.06
    家庭
    0.06
     kontakt
    0.06
     حم
    0.06
    (TRUE
    0.06
    !")↵↵
    0.06
     bacter
    0.06
    parameter
    0.06
    Act Density 0.004%

    No Known Activations