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

    Neuronpedia

    INDEX
    Explanations

    scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ULA
    -0.07
    Challenge
    -0.06
     church
    -0.06
    .relative
    -0.06
    .Cache
    -0.06
    Zero
    -0.06
    UINT
    -0.06
    Expr
    -0.06
    	start
    -0.06
    .Child
    -0.06
    POSITIVE LOGITS
     профес
    0.07
     serviço
    0.07
    iště
    0.07
    {},↵
    0.06
     declar
    0.06
     sout
    0.06
     userid
    0.06
    olet
    0.06
     Дж
    0.06
     вед
    0.06
    Act Density 0.127%

    No Known Activations