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

    Neuronpedia

    INDEX
    Explanations

    aware

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۲۷
    -0.07
    建设
    -0.07
     zákaz
    -0.07
     úkol
    -0.06
    孙
    -0.06
    仲
    -0.06
    ابعة
    -0.06
    建設
    -0.06
    ended
    -0.06
    tract
    -0.06
    POSITIVE LOGITS
     aware
    0.11
     awareness
    0.09
     Awareness
    0.07
     Aware
    0.06
    #echo
    0.06
     sweeps
    0.06
     getTime
    0.06
     unaware
    0.06
    entionPolicy
    0.06
     know
    0.06
    Act Density 0.010%

    No Known Activations