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

    Neuronpedia

    INDEX
    Explanations

    a/an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sommes
    -0.07
     dikke
    -0.07
    תרג
    -0.07
     manned
    -0.07
    lossen
    -0.07
    שני
    -0.06
    进博会
    -0.06
    .Must
    -0.06
    ꞊
    -0.06
     embry
    -0.06
    POSITIVE LOGITS
    ....
    0.08
    앴
    0.07
    ivery
    0.07
    행
    0.07
    路线
    0.06
    ('.
    0.06
    uits
    0.06
     fires
    0.06
     bail
    0.06
    金币
    0.06
    Act Density 0.023%

    No Known Activations