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

    Neuronpedia

    INDEX
    Explanations

    software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᨬ
    -0.07
     Bik
    -0.07
     Dee
    -0.07
     BUSINESS
    -0.06
    anga
    -0.06
    欧
    -0.06
     links
    -0.06
    notes
    -0.06
    anvas
    -0.06
    éparation
    -0.06
    POSITIVE LOGITS
    entionPolicy
    0.08
    [event
    0.07
    "Don
    0.07
     Denn
    0.07
     gioc
    0.07
    מחיר
    0.07
    Labor
    0.06
    nesc
    0.06
    _race
    0.06
    💸
    0.06
    Act Density 0.117%

    No Known Activations