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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meiden
    -0.07
    Biz
    -0.07
     Moose
    -0.06
     preacher
    -0.06
     참
    -0.06
     congregation
    -0.06
     inevitable
    -0.06
    闲
    -0.06
     heaters
    -0.06
     chats
    -0.06
    POSITIVE LOGITS
     Nicholas
    0.12
     Steven
    0.10
     Kenneth
    0.09
     Christopher
    0.09
     Timothy
    0.08
     Gerald
    0.08
    Steven
    0.08
     Stephen
    0.08
    Christopher
    0.08
     Samuel
    0.07
    Act Density 0.051%

    No Known Activations