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

    Neuronpedia

    INDEX
    Explanations

    mathematical proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Medicare
    -0.07
    _annotations
    -0.07
     Paint
    -0.06
    _xyz
    -0.06
     eller
    -0.06
    회
    -0.06
     Healthcare
    -0.06
    에서
    -0.06
     surgeons
    -0.06
    Descriptors
    -0.06
    POSITIVE LOGITS
    //================================================================
    0.07
    sorting
    0.06
    оло
    0.06
    	prop
    0.06
     голова
    0.06
    .getMonth
    0.06
    ;;↵
    0.06
     Gul
    0.06
     cere
    0.06
    	puts
    0.06
    Act Density 0.009%

    No Known Activations