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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Walker
    -0.08
     concentrated
    -0.07
     capturing
    -0.06
     Kur
    -0.06
     Powder
    -0.06
     hunt
    -0.06
     colonial
    -0.06
     Buckley
    -0.06
     dismissal
    -0.06
     disposal
    -0.06
    POSITIVE LOGITS
     xmlhttp
    0.08
     قاب
    0.07
     milfs
    0.07
    џџџџ
    0.06
    @Xml
    0.06
    เฉ
    0.06
     hypocrisy
    0.06
    ใส
    0.06
    GameData
    0.06
     upheld
    0.06
    Act Density 0.023%

    No Known Activations