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

    Neuronpedia

    INDEX
    Explanations

    research reporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	iter
    -0.07
     Sl
    -0.07
     France
    -0.06
     Ju
    -0.06
    四
    -0.06
    Sl
    -0.06
     attacking
    -0.06
    -prop
    -0.06
     Millet
    -0.06
    Ar
    -0.06
    POSITIVE LOGITS
    >"
    0.06
     Terms
    0.06
    ILON
    0.06
    JOR
    0.06
     unsure
    0.06
    яти
    0.06
    "][
    0.06
    ALLED
    0.06
    asyon
    0.06
    (confirm
    0.06
    Act Density 0.003%

    No Known Activations