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

    Neuronpedia

    INDEX
    Explanations

    Chemical compounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    疥
    -0.08
    เข
    -0.07
    햄
    -0.07
    ⒜
    -0.07
     travel
    -0.07
     run
    -0.06
    קרה
    -0.06
    -dismiss
    -0.06
    kill
    -0.06
    回忆
    -0.06
    POSITIVE LOGITS
    idity
    0.08
    وات
    0.07
    ading
    0.07
     Wimbledon
    0.07
    0.07
    𝘯
    0.07
    乱象
    0.07
    ỵ
    0.06
    च
    0.06
    LEE
    0.06
    Act Density 0.002%

    No Known Activations