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

    Neuronpedia

    INDEX
    Explanations

    chemical processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rh
    -0.07
    Rh
    -0.06
    structions
    -0.06
     ref
    -0.06
    (em
    -0.06
     cx
    -0.06
     caught
    -0.06
    界
    -0.06
     Caught
    -0.06
    _word
    -0.06
    POSITIVE LOGITS
    django
    0.07
     страш
    0.07
    .TextEdit
    0.07
     sécur
    0.07
     namoro
    0.06
    нівер
    0.06
     Commons
    0.06
     careers
    0.06
     Marines
    0.06
    iệu
    0.06
    Act Density 0.013%

    No Known Activations