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

    Neuronpedia

    INDEX
    Explanations

    awareness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     objected
    -0.07
    ثال
    -0.07
     gg
    -0.07
    /Delete
    -0.07
     Tillerson
    -0.07
    _three
    -0.07
    _left
    -0.07
    text
    -0.07
     работу
    -0.07
     ("
    -0.07
    POSITIVE LOGITS
    lásil
    0.09
     Awareness
    0.09
     awareness
    0.07
    OUS
    0.06
     Sidebar
    0.06
    _perc
    0.06
    aff
    0.06
    arser
    0.06
     Ard
    0.06
    (schema
    0.06
    Act Density 0.010%

    No Known Activations