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

    Neuronpedia

    INDEX
    Explanations

    self-awareness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     siè
    -0.07
     сф
    -0.06
     summarized
    -0.06
     pomp
    -0.06
     pdata
    -0.06
     altura
    -0.06
    	printf
    -0.06
     Mitarbeiter
    -0.06
     systém
    -0.06
     bows
    -0.06
    POSITIVE LOGITS
    _typeof
    0.09
    egree
    0.07
    cab
    0.06
    216
    0.06
    Dem
    0.06
     Pose
    0.06
    templ
    0.06
     pravděpodob
    0.06
    Variable
    0.06
     REV
    0.06
    Act Density 0.057%

    No Known Activations