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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τέρα
    -0.07
    偷
    -0.07
    -terrorism
    -0.06
    .Win
    -0.06
    AIT
    -0.06
    Struct
    -0.06
     liberation
    -0.06
     fairy
    -0.06
     Mp
    -0.06
     mascot
    -0.06
    POSITIVE LOGITS
    AGIC
    0.07
    ραση
    0.07
    大學
    0.06
    siz
    0.06
     들어
    0.06
    ाठ
    0.06
    .Handler
    0.06
    еди
    0.06
    )</
    0.06
    order
    0.06
    Act Density 0.010%

    No Known Activations