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

    Neuronpedia

    INDEX
    Explanations

    been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FX
    -0.07
    ництва
    -0.06
     přiv
    -0.06
    Cr
    -0.06
    ранения
    -0.06
     spoiler
    -0.06
     ^^
    -0.06
    UMP
    -0.06
     billboard
    -0.06
     всього
    -0.06
    POSITIVE LOGITS
     Allies
    0.07
     discretion
    0.06
    ?</
    0.06
    CONST
    0.06
     spont
    0.06
     end
    0.06
     بند
    0.06
    izio
    0.06
     หล
    0.06
    (Method
    0.06
    Act Density 0.038%

    No Known Activations