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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _lifetime
    -0.07
    lict
    -0.07
    ----------------------------------------------------------------------------
    -0.07
    илання
    -0.07
    xoops
    -0.06
     standings
    -0.06
     Craigslist
    -0.06
    	holder
    -0.06
    ‘
    -0.06
    اضی
    -0.06
    POSITIVE LOGITS
     Released
    0.06
     sculpt
    0.06
    warnings
    0.06
    तर
    0.06
     цей
    0.06
     ape
    0.05
     Aware
    0.05
     DOI
    0.05
     λεπ
    0.05
     Beds
    0.05
    Act Density 0.010%

    No Known Activations