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

    Neuronpedia

    INDEX
    Explanations

    chapter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UGINS
    -0.07
    ackbar
    -0.06
     goodwill
    -0.06
    udiante
    -0.06
     บาง
    -0.06
    _SHA
    -0.06
    outs
    -0.06
     urls
    -0.06
     crashing
    -0.06
    ulace
    -0.06
    POSITIVE LOGITS
     ignor
    0.07
    结束
    0.06
     surpassed
    0.06
     حساب
    0.06
     gener
    0.06
     arises
    0.06
     CENT
    0.06
     Favorite
    0.06
     Forum
    0.06
    序
    0.06
    Act Density 0.014%

    No Known Activations