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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Andersen
    -0.09
     frei
    -0.07
     adel
    -0.07
     Giov
    -0.07
    STRU
    -0.07
    klär
    -0.07
     whispered
    -0.06
    (del
    -0.06
    茁
    -0.06
     crispy
    -0.06
    POSITIVE LOGITS
     Authentication
    0.07
     minimise
    0.07
    一些
    0.07
    	start
    0.07
     faculties
    0.06
     respectable
    0.06
    JECT
    0.06
    풉
    0.06
     inflicted
    0.06
    pike
    0.06
    Act Density 0.068%

    No Known Activations