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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Loft
    -0.07
    (Auth
    -0.07
     embracing
    -0.07
    (plugin
    -0.06
     Studi
    -0.06
     volunteering
    -0.06
    [tmp
    -0.06
     autom
    -0.06
    :[[
    -0.06
    _MAY
    -0.06
    POSITIVE LOGITS
     jc
    0.06
    πή
    0.06
    ис
    0.06
     �
    0.06
     debts
    0.06
    σαν
    0.06
    þ
    0.06
     acct
    0.06
    .resp
    0.06
    -worthy
    0.06
    Act Density 0.003%

    No Known Activations